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

    Neuronpedia

    INDEX
    Explanations

    technical and scientific

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .local
    -0.07
    held
    -0.07
    <Token
    -0.07
    μέν
    -0.07
     Compile
    -0.07
    ToBounds
    -0.07
     back
    -0.07
     fire
    -0.06
    職
    -0.06
    (instr
    -0.06
    POSITIVE LOGITS
     VE
    0.06
    PU
    0.06
    **(
    0.06
    724
    0.06
    різ
    0.06
     erm
    0.06
    ünü
    0.06
    asyarak
    0.06
    ilarity
    0.06
     fueled
    0.06
    Act Density 0.046%

    No Known Activations