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

    Neuronpedia

    INDEX
    Explanations

    author names in academic or research contexts

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

    section titles and metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.99
     queſta
    -0.93
     $_"
    -0.84
    migrationBuilder
    -0.84
    ſſung
    -0.84
     betweenstory
    -0.83
     CanadaChoose
    -0.82
     $_(
    -0.82
    RTGC
    -0.81
    tagHelperRunner
    -0.81
    POSITIVE LOGITS
    2
    0.45
    I
    0.42
    1
    0.41
    0
    0.39
    9
    0.38
    3
    0.38
    4
    0.37
                
    0.36
     I
    0.36
    5
    0.35
    Act Density 0.001%

    No Known Activations