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

    Neuronpedia

    INDEX
    Explanations

    uses of the word "cause" alongside words related to measurement and preservation.

    oai_token-act-pair · gemini-2.0-flash

    cause

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <eos>
    -0.84
    ↵
    -0.80
     form
    -0.79
     un
    -0.73
     
    -0.72
     le
    -0.67
     Me
    -0.66
     la
    -0.66
     com
    -0.65
    form
    -0.65
    POSITIVE LOGITS
     ainfi
    1.60
     étoient
    1.55
     feroit
    1.52
     avoient
    1.49
     anún
    1.49
     étoit
    1.47
     auroit
    1.46
     Monfieur
    1.43
     pouvoit
    1.43
     Theſe
    1.41
    Act Density 1.957%

    No Known Activations