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

    Neuronpedia

    INDEX
    Explanations

    court cases and MIT research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .item
    -0.07
    .Dep
    -0.07
    _popup
    -0.07
    _PK
    -0.06
    _p
    -0.06
    év
    -0.06
    .column
    -0.06
    BR
    -0.06
    boo
    -0.06
     widened
    -0.06
    POSITIVE LOGITS
     हट
    0.07
    において
    0.06
    quest
    0.06
     strongest
    0.06
     Garrett
    0.06
     nového
    0.06
     udělat
    0.06
     právo
    0.06
    NSUInteger
    0.06
    oise
    0.06
    Act Density 0.000%

    No Known Activations