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

    Neuronpedia

    INDEX
    Explanations

    miss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     		↵
    -0.07
     dubbed
    -0.06
    谎
    -0.06
    ArrayList
    -0.06
    -era
    -0.06
    ⊅
    -0.06
    豳
    -0.06
     whims
    -0.06
    --}}↵
    -0.06
    𠮷
    -0.06
    POSITIVE LOGITS
    isEqual
    0.08
    حمام
    0.07
     destroys
    0.07
     metall
    0.07
    rece
    0.07
    Utilities
    0.07
    达到
    0.07
    inte
    0.07
    ุง
    0.07
     Stamford
    0.07
    Act Density 0.003%

    No Known Activations