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

    Neuronpedia

    INDEX
    Explanations

    expresses interest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rất
    -0.07
     Cand
    -0.07
     pozn
    -0.06
     Sle
    -0.06
     lang
    -0.06
    808
    -0.06
     Subaru
    -0.06
     Tat
    -0.06
     undergo
    -0.06
    ensch
    -0.06
    POSITIVE LOGITS
    icare
    0.07
    (-(
    0.07
     dù
    0.06
     mensaje
    0.06
     기반
    0.06
    filtro
    0.06
    inoa
    0.06
    TRAIN
    0.06
    ppo
    0.06
    èmes
    0.06
    Act Density 0.173%

    No Known Activations