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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ),'
    -0.07
    )=
    -0.07
    ▍
    -0.07
    _RA
    -0.06
    EO
    -0.06
    _overflow
    -0.06
     Gdk
    -0.06
     NSNumber
    -0.06
    =c
    -0.06
    gence
    -0.06
    POSITIVE LOGITS
     intimidate
    0.07
    otros
    0.07
    Esta
    0.07
    	mv
    0.07
    FTA
    0.06
    eras
    0.06
    sla
    0.06
    bef
    0.06
     tüket
    0.06
    744
    0.06
    Act Density 0.000%

    No Known Activations