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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ",__
    -0.06
    .initState
    -0.06
     "\""
    -0.06
    ihil
    -0.06
    .Fragment
    -0.06
    amines
    -0.06
     GA
    -0.06
     Delta
    -0.06
     Gaw
    -0.06
    eed
    -0.06
    POSITIVE LOGITS
    pections
    0.06
    γκε
    0.06
    senha
    0.06
     eapply
    0.06
    .nb
    0.06
    forget
    0.06
     отвер
    0.06
    anglicky
    0.06
     inj
    0.06
     áll
    0.06
    Act Density 0.316%

    No Known Activations