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

    Neuronpedia

    INDEX
    Explanations

    halluc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Decl
    -0.07
     opat
    -0.06
    uniacid
    -0.06
    "]');↵
    -0.06
    (pk
    -0.06
    _KIND
    -0.06
    _amt
    -0.06
     renders
    -0.06
     memiliki
    -0.06
     lazy
    -0.06
    POSITIVE LOGITS
     should
    0.07
     vời
    0.07
     recognise
    0.07
     music
    0.06
    	pr
    0.06
     SHOULD
    0.06
     Transmission
    0.06
     Counts
    0.06
    Fantastic
    0.06
     свет
    0.06
    Act Density 0.001%

    No Known Activations