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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Penalty
    -0.07
    _mime
    -0.07
     Amateur
    -0.06
    currentTime
    -0.06
     أمر
    -0.06
    计划
    -0.06
     waged
    -0.06
    일에
    -0.06
    .page
    -0.06
     státy
    -0.06
    POSITIVE LOGITS
    раст
    0.07
    ینگ
    0.07
     execute
    0.07
    .spark
    0.07
     CAST
    0.07
    SB
    0.06
     zw
    0.06
    ská
    0.06
     GB
    0.06
     DR
    0.06
    Act Density 0.022%

    No Known Activations