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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sand
    -0.08
    칵
    -0.07
     handle
    -0.07
    bind
    -0.07
    Multiplicity
    -0.07
    inspect
    -0.07
    -ranked
    -0.07
     абсолютно
    -0.07
    克拉
    -0.07
    最难
    -0.07
    POSITIVE LOGITS
    (datos
    0.07
     �
    0.07
    lectual
    0.07
    ึก
    0.07
     uni
    0.07
    >/<
    0.07
    �
    0.07
    _return
    0.06
    >I
    0.06
    -zero
    0.06
    Act Density 0.040%

    No Known Activations