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

    Neuronpedia

    INDEX
    Explanations

    commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     _:
    -0.07
     announcements
    -0.07
     وما
    -0.07
    thought
    -0.06
     DETAILS
    -0.06
    stress
    -0.06
     Or
    -0.06
    htags
    -0.06
    |.
    -0.06
     UPS
    -0.06
    POSITIVE LOGITS
     inexp
    0.08
    ивается
    0.07
    'use
    0.06
     residual
    0.06
    .Fragment
    0.06
     دول
    0.06
    gorithm
    0.06
    Mock
    0.06
    nature
    0.06
    :`
    0.06
    Act Density 0.214%

    No Known Activations