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

    Neuronpedia

    INDEX
    Explanations

    FROM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Daily
    -0.07
    Mp
    -0.07
    belt
    -0.06
    _MAY
    -0.06
    -capital
    -0.06
    ovement
    -0.06
     justification
    -0.06
    Failure
    -0.06
    .deep
    -0.06
     Pepper
    -0.06
    POSITIVE LOGITS
    initWith
    0.06
    ていた
    0.06
     Üy
    0.06
    <u
    0.06
     undesirable
    0.06
    VG
    0.06
    حی
    0.06
     ue
    0.06
    unistd
    0.06
     yapmak
    0.06
    Act Density 0.002%

    No Known Activations