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

    Neuronpedia

    INDEX
    Explanations

    time passing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     concession
    -0.07
    �
    -0.06
    '>";↵
    -0.06
     diz
    -0.06
    可
    -0.06
     gorgeous
    -0.06
     negate
    -0.06
     Rhode
    -0.06
    Limits
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    .s
    0.07
    annot
    0.07
    ４
    0.06
    faith
    0.06
    Quaternion
    0.06
     minutos
    0.06
    _gui
    0.06
     humility
    0.06
    .measure
    0.06
    瞬
    0.06
    Act Density 0.025%

    No Known Activations