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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    我认为
    -0.07
    cola
    -0.07
    .checkbox
    -0.07
    otoxic
    -0.07
     Ek
    -0.07
    띔
    -0.07
    诃
    -0.06
     additives
    -0.06
     Terror
    -0.06
    _boolean
    -0.06
    POSITIVE LOGITS
     generations
    0.07
    жи
    0.07
    -registration
    0.07
    三大阶段
    0.07
     che
    0.07
    🧞
    0.07
    know
    0.06
    场
    0.06
     spikes
    0.06
    =@
    0.06
    Act Density 0.017%

    No Known Activations