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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hey
    -0.07
    Dry
    -0.06
    alnız
    -0.06
     ру
    -0.06
     Dry
    -0.06
    _IMM
    -0.06
     dry
    -0.06
    (points
    -0.06
    provide
    -0.06
    #######↵
    -0.06
    POSITIVE LOGITS
     firepower
    0.07
     důvod
    0.07
    lsruhe
    0.06
    례
    0.06
     evolution
    0.06
     swath
    0.06
     Poz
    0.06
     bilinen
    0.06
    Containing
    0.06
     BrowserAnimationsModule
    0.06
    Act Density 0.032%

    No Known Activations