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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to explanations or justifications

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

    causes and justifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dalamnya
    -0.38
     spetta
    -0.36
     asupra
    -0.36
    맙
    -0.35
     argint
    -0.35
     zuges
    -0.35
     ubezpiec
    -0.35
    gnügen
    -0.34
    sätzlich
    -0.34
     Dinamarca
    -0.34
    POSITIVE LOGITS
     reason
    1.51
     Reason
    1.45
     reasons
    1.40
    reason
    1.38
    Reason
    1.37
     Reasons
    1.37
    Reasons
    1.30
    reasons
    1.23
    REASON
    1.22
     REASON
    1.21
    Act Density 0.045%

    No Known Activations