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

    Neuronpedia

    INDEX
    Explanations

    scale to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    文创
    -0.07
    ייס
    -0.06
     VIR
    -0.06
    风情
    -0.06
    짱
    -0.06
    葡萄
    -0.06
    باس
    -0.06
     الأجنب
    -0.06
    /ng
    -0.06
    风暴
    -0.06
    POSITIVE LOGITS
    Oil
    0.07
    Former
    0.07
     dil
    0.07
    -exc
    0.07
    _hero
    0.07
    shaft
    0.07
    �
    0.07
    .po
    0.07
    Moves
    0.07
    pheric
    0.06
    Act Density 0.001%

    No Known Activations