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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    !!!!!
    -0.06
    (".")
    -0.06
     hayır
    -0.06
    .bd
    -0.06
     Apex
    -0.06
     fazla
    -0.06
    .Matchers
    -0.06
    爷
    -0.06
    _yaml
    -0.06
    :::::::::::::::
    -0.06
    POSITIVE LOGITS
    undaki
    0.07
    discount
    0.07
     dilemma
    0.07
     respects
    0.07
     pretext
    0.06
     pública
    0.06
    _market
    0.06
    :::/
    0.06
    -volume
    0.06
     constituency
    0.06
    Act Density 0.000%

    No Known Activations