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

    Neuronpedia

    INDEX
    Explanations

    Comics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Color
    -0.07
     emphasize
    -0.06
     computed
    -0.06
     праці
    -0.06
    survey
    -0.06
     emphasized
    -0.06
     watching
    -0.06
    .say
    -0.06
    _targets
    -0.06
     stores
    -0.06
    POSITIVE LOGITS
    autorelease
    0.06
     Hizmet
    0.06
     Verd
    0.06
    everything
    0.06
    Network
    0.06
     あ
    0.06
     rewriting
    0.06
    �
    0.06
    members
    0.06
    ौत
    0.06
    Act Density 0.015%

    No Known Activations