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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    颅
    -0.08
    镇江
    -0.07
     heed
    -0.07
    izados
    -0.07
    依赖
    -0.07
     Through
    -0.07
     tracing
    -0.07
     Leaves
    -0.07
     pis
    -0.07
     Germans
    -0.07
    POSITIVE LOGITS
     counterpart
    0.07
    (define
    0.07
     siguientes
    0.07
    ⬡
    0.07
    ऑ
    0.06
    ﳥ
    0.06
    bbb
    0.06
    .currentTarget
    0.06
    [last
    0.06
    (Bytes
    0.06
    Act Density 0.002%

    No Known Activations