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

    Neuronpedia

    INDEX
    Explanations

    Tensor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ci
    -0.07
    aub
    -0.06
     vl
    -0.06
     Elm
    -0.06
    	org
    -0.06
    vj
    -0.06
    494
    -0.06
    develop
    -0.06
    �
    -0.06
    vey
    -0.06
    POSITIVE LOGITS
    \core
    0.08
    .tensor
    0.08
     Tes
    0.07
    ěn
    0.07
    σεων
    0.07
     Feast
    0.07
    _fn
    0.07
     rencontres
    0.07
    損
    0.06
    _successful
    0.06
    Act Density 0.003%

    No Known Activations