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

    Neuronpedia

    INDEX
    Explanations

    alternative world

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     argc
    -0.07
    ?,?,?,?,
    -0.06
     cep
    -0.06
    �
    -0.06
    Begin
    -0.06
     Phelps
    -0.06
     ukon
    -0.06
    Dic
    -0.06
    Є
    -0.06
     Ents
    -0.06
    POSITIVE LOGITS
     creditors
    0.08
     supervise
    0.07
     negotiated
    0.07
     (<
    0.07
     (+
    0.07
    _Selection
    0.07
     coined
    0.07
    _config
    0.07
     peru
    0.07
     Osmanlı
    0.06
    Act Density 0.066%

    No Known Activations