Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific forms and structures related to sentences and clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    German language and code-related terms

    np_acts-logits-general · gemini-2.0-flash

    einen ( copy ( 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onCancelled
    -0.60
    źnie
    -0.60
     iodide
    -0.56
    migrationBuilder
    -0.54
     frågor
    -0.54
     bromide
    -0.53
    mography
    -0.52
     halide
    -0.51
     betweenstory
    -0.50
     Carmine
    -0.49
    POSITIVE LOGITS
     Deal
    0.58
     Code
    0.58
     anyway
    0.54
     deal
    0.53
    Code
    0.50
     <<<<<<<<<<<<<<
    0.50
     Gang
    0.48
     Look
    0.47
     Ansatz
    0.45
     Auftritt
    0.44
    Act Density 0.008%

    No Known Activations