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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    GetProcAddress
    -0.07
    锑
    -0.07
    mètre
    -0.07
    istringstream
    -0.07
    Aspect
    -0.07
    */),
    -0.07
    玃
    -0.07
    墕
    -0.07
     mush
    -0.07
    POSITIVE LOGITS
    യ
    0.08
     justify
    0.07
     offender
    0.07
     成
    0.07
     Projects
    0.07
    oun
    0.06
     malloc
    0.06
    .TH
    0.06
    选�
    0.06
    third
    0.06
    Act Density 0.014%

    No Known Activations