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

    Neuronpedia

    INDEX
    Explanations

    speech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utilisons
    -0.69
     itſelf
    -0.60
     ―――――
    -0.59
    issaient
    -0.58
    ftagPool
    -0.58
     Monfieur
    -0.57
     gehör
    -0.57
     cdti
    -0.56
    ValueGeneration
    -0.56
    soever
    -0.55
    POSITIVE LOGITS
    ...
    0.63
    :
    0.60
    ....
    0.54
     on
    0.54
    :
    0.53
     Feb
    0.53
    …
    0.52
     this
    0.51
     ...
    0.50
    ..
    0.49
    Act Density 0.055%

    No Known Activations