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

    Neuronpedia

    INDEX
    Explanations

    reference markers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rust
    -0.06
    belongsTo
    -0.06
     Swift
    -0.06
    invisible
    -0.06
    보
    -0.06
    JsonObject
    -0.06
     fists
    -0.06
     Good
    -0.06
     midd
    -0.06
     he
    -0.06
    POSITIVE LOGITS
    )[-
    0.06
    �체
    0.06
    ιστο
    0.06
    ini
    0.06
    )((((
    0.06
    rottle
    0.06
    �
    0.05
     transformation
    0.05
    _PLAY
    0.05
     novelty
    0.05
    Act Density 0.040%

    No Known Activations