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

    Neuronpedia

    INDEX
    Explanations

    management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mec
    -0.06
     Nurs
    -0.06
     kein
    -0.06
     softly
    -0.06
     hoş
    -0.06
    貌
    -0.06
     نوف
    -0.06
     admitting
    -0.06
    .ref
    -0.06
    ู
    -0.06
    POSITIVE LOGITS
    quist
    0.07
    _ctl
    0.07
     responders
    0.07
    agy
    0.07
    -player
    0.07
    hexdigest
    0.07
    ('*
    0.07
    Workflow
    0.07
    ride
    0.07
    ным
    0.07
    Act Density 0.034%

    No Known Activations