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

    Neuronpedia

    INDEX
    Explanations

    Carolina

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Vector
    -0.07
    .cell
    -0.07
     predicts
    -0.06
    --------↵↵
    -0.06
    ComboBox
    -0.06
     Nottingham
    -0.06
     industries
    -0.06
    ै?
    -0.06
    夫
    -0.06
    Dataset
    -0.06
    POSITIVE LOGITS
     OnCollision
    0.07
    ORLD
    0.07
    indice
    0.06
     secluded
    0.06
    (secret
    0.06
    (HTTP
    0.06
    _Ph
    0.06
     FEMA
    0.06
     ages
    0.06
     vå
    0.06
    Act Density 0.027%

    No Known Activations