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

    Neuronpedia

    INDEX
    Explanations

    online class locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     debut
    -0.07
    False
    -0.06
    Depth
    -0.06
     attrib
    -0.06
    _ARGUMENT
    -0.06
     sprayed
    -0.06
    ryption
    -0.05
     bladder
    -0.05
     prizes
    -0.05
    ён
    -0.05
    POSITIVE LOGITS
     �
    0.07
    (global
    0.07
    ılığıyla
    0.07
     Flexible
    0.06
    .softmax
    0.06
     вік
    0.06
    (__('
    0.06
     Positioned
    0.06
    сім
    0.06
    cxx
    0.06
    Act Density 0.000%

    No Known Activations