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

    Neuronpedia

    INDEX
    Explanations

    prevalence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shadows
    -0.07
     المغرب
    -0.07
    Ｌ
    -0.06
     PDT
    -0.06
     Finite
    -0.06
    як
    -0.06
     Mills
    -0.06
    dealloc
    -0.06
     Karachi
    -0.06
     Sears
    -0.06
    POSITIVE LOGITS
    .....
    0.06
    @endif
    0.06
     کوه
    0.06
     ";↵↵
    0.06
     ListItem
    0.06
     αξ
    0.06
     follows
    0.05
    _VIS
    0.05
     development
    0.05
     trusted
    0.05
    Act Density 0.038%

    No Known Activations