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

    Neuronpedia

    INDEX
    Explanations

    increase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    escort
    -0.07
    ayas
    -0.06
    riot
    -0.06
    eer
    -0.06
    ียรต
    -0.06
    _columns
    -0.06
    stateParams
    -0.06
    уватися
    -0.06
     reins
    -0.06
    emption
    -0.06
    POSITIVE LOGITS
    VERSION
    0.07
     increase
    0.07
     resort
    0.07
     نقش
    0.07
     طی
    0.06
    提升
    0.06
    (month
    0.06
    欲
    0.06
    nv
    0.06
    प
    0.06
    Act Density 0.039%

    No Known Activations