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

    Neuronpedia

    INDEX
    Explanations

    stage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UIFont
    -0.06
     đổ
    -0.06
    utin
    -0.06
     مف
    -0.06
    ustum
    -0.06
    .М
    -0.06
     Další
    -0.06
    _xlabel
    -0.05
    عف
    -0.05
    _tuple
    -0.05
    POSITIVE LOGITS
    _message
    0.07
     SHARE
    0.07
     PS
    0.07
     sik
    0.07
     finishing
    0.06
     defensively
    0.06
     sher
    0.06
     tick
    0.06
     grupo
    0.06
     νεφοκ
    0.06
    Act Density 0.007%

    No Known Activations