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

    Neuronpedia

    INDEX
    Explanations

    decision

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    062
    -0.07
    _loc
    -0.07
    radius
    -0.06
    _spaces
    -0.06
    Ghost
    -0.06
    circ
    -0.06
    112
    -0.06
     eing
    -0.06
    ToList
    -0.06
    charted
    -0.06
    POSITIVE LOGITS
     decision
    0.08
    ems
    0.08
     choice
    0.06
     hasil
    0.06
     Ngành
    0.06
     내
    0.06
    .Many
    0.06
    uesto
    0.06
    PullParser
    0.06
     seventy
    0.06
    Act Density 0.035%

    No Known Activations