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

    Neuronpedia

    INDEX
    Explanations

    Quotation punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     homeschool
    -0.09
    Therefore
    -0.07
    ricks
    -0.07
    Write
    -0.07
     writing
    -0.07
     findings
    -0.07
     Serialization
    -0.07
     simples
    -0.06
    grid
    -0.06
     RV
    -0.06
    POSITIVE LOGITS
    aceut
    0.07
     Italians
    0.06
    -exp
    0.06
     nao
    0.06
     Getting
    0.06
    -launch
    0.06
     Пет
    0.06
    ()=>
    0.06
     debilitating
    0.06
    ře
    0.06
    Act Density 0.007%

    No Known Activations