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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     꿈
    -0.07
     LinearGradient
    -0.07
     dbus
    -0.06
    ίσ
    -0.06
     blanks
    -0.06
     примерно
    -0.06
     Dirt
    -0.06
    .tokenize
    -0.06
    .moveTo
    -0.06
     díky
    -0.06
    POSITIVE LOGITS
    respond
    0.08
    NY
    0.07
     tarih
    0.06
    phen
    0.06
    pled
    0.06
    clang
    0.06
    rgan
    0.06
    avatar
    0.06
    Shortcut
    0.06
    izontally
    0.06
    Act Density 0.053%

    No Known Activations