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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    שטח
    -0.08
    👦
    -0.07
     synthesis
    -0.07
     sigh
    -0.07
    ıt
    -0.07
    }')↵
    -0.07
    ⦿
    -0.07
    看电视
    -0.07
     ngọ
    -0.07
    }}"↵
    -0.07
    POSITIVE LOGITS
    充满了
    0.07
    orneys
    0.07
    \Collection
    0.07
    本网
    0.07
     메
    0.07
    .uk
    0.07
    ку
    0.07
     Nicole
    0.07
    拽
    0.07
    _k
    0.07
    Act Density 0.045%

    No Known Activations