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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ниже
    -0.07
     DevExpress
    -0.07
    (pattern
    -0.07
    Monkey
    -0.07
    _DISTANCE
    -0.07
    togroup
    -0.07
    GRE
    -0.07
     Sys
    -0.06
     вип
    -0.06
    .SetToolTip
    -0.06
    POSITIVE LOGITS
     ifade
    0.06
     knots
    0.06
    ancing
    0.06
    234
    0.06
     implications
    0.06
     Proxy
    0.06
     ever
    0.06
     val
    0.06
     لا
    0.06
    >In
    0.06
    Act Density 0.016%

    No Known Activations