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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gas
    -0.06
     chains
    -0.06
     yer
    -0.06
    general
    -0.06
     Gand
    -0.06
    RESS
    -0.06
     ambitious
    -0.06
     Communications
    -0.06
     έργ
    -0.06
     Georgetown
    -0.06
    POSITIVE LOGITS
    Needed
    0.07
    .favorite
    0.07
    .all
    0.06
     darker
    0.06
     삭제
    0.06
     redhead
    0.06
    .pageY
    0.06
     donde
    0.06
    telefone
    0.06
    ayın
    0.06
    Act Density 0.025%

    No Known Activations