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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jb
    -0.07
     eminent
    -0.07
     starší
    -0.06
    formance
    -0.06
     псих
    -0.06
    _io
    -0.06
    .dt
    -0.06
     dt
    -0.06
     фак
    -0.06
     Crush
    -0.06
    POSITIVE LOGITS
    ][]
    0.06
    upportInitialize
    0.06
     PdfP
    0.06
    assigned
    0.06
     �
    0.06
    NullOr
    0.06
     cleans
    0.06
     тран
    0.06
     {}));↵
    0.06
    ,bool
    0.06
    Act Density 0.010%

    No Known Activations