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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sound
    -0.08
    OO
    -0.07
     Skinner
    -0.07
     Whe
    -0.07
     built
    -0.06
     �
    -0.06
    .ReadInt
    -0.06
     Erg
    -0.06
    instruction
    -0.06
     covered
    -0.06
    POSITIVE LOGITS
     محاس
    0.07
     первый
    0.07
    rror
    0.06
    .sun
    0.06
    ESIS
    0.06
    παίδ
    0.06
    Continue
    0.06
     CHAR
    0.06
     者
    0.06
    _macros
    0.06
    Act Density 0.005%

    No Known Activations