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

    Neuronpedia

    INDEX
    Explanations

    code licenses and copyright

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ivated
    -0.07
    getFile
    -0.07
     ${↵
    -0.07
    umatic
    -0.07
    甘肃
    -0.07
    去过
    -0.07
     TypeScript
    -0.06
    优良
    -0.06
    bone
    -0.06
    植被
    -0.06
    POSITIVE LOGITS
    諸
    0.08
    łó
    0.08
     challenger
    0.07
    _friend
    0.07
    طبع
    0.07
    讽
    0.07
     리
    0.07
    eric
    0.06
    empresa
    0.06
    לוק
    0.06
    Act Density 0.003%

    No Known Activations