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

    Neuronpedia

    INDEX
    Explanations

    Instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inclination
    -0.07
     предвар
    -0.07
    _cod
    -0.07
    руз
    -0.07
     Morris
    -0.07
    retain
    -0.06
     unravel
    -0.06
     bew
    -0.06
    aptured
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     Casting
    0.06
    acist
    0.06
    AUDIO
    0.06
     whipped
    0.06
    ุญาต
    0.06
     Jobs
    0.05
    ㎡(
    0.05
    istribute
    0.05
    _REFERER
    0.05
    .hover
    0.05
    Act Density 0.067%

    No Known Activations