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

    Neuronpedia

    INDEX
    Explanations

    agents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    íž
    -0.07
     spécial
    -0.07
    uzu
    -0.07
    альному
    -0.06
    wig
    -0.06
    acci
    -0.06
    -sex
    -0.06
    recursive
    -0.06
    MARY
    -0.06
    imizde
    -0.06
    POSITIVE LOGITS
     rebound
    0.07
    ADOW
    0.06
     imageUrl
    0.06
    �
    0.06
    (slot
    0.06
    .Future
    0.06
    <Project
    0.06
    .Position
    0.06
     После
    0.06
    \Action
    0.06
    Act Density 0.000%

    No Known Activations