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

    Neuronpedia

    INDEX
    Explanations

    legal/copyright information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     misunderstand
    -0.07
    龁
    -0.07
     Tek
    -0.07
    <State
    -0.07
     Nancy
    -0.07
     notwithstanding
    -0.06
    贫血
    -0.06
    __()↵
    -0.06
    مم
    -0.06
    桌子上
    -0.06
    POSITIVE LOGITS
    .Instance
    0.07
    wn
    0.07
    _labels
    0.07
    ayers
    0.06
     tuition
    0.06
     PAY
    0.06
     brake
    0.06
    关税
    0.06
    beiten
    0.06
    筌
    0.06
    Act Density 0.000%

    No Known Activations