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

    Neuronpedia

    INDEX
    Explanations

    code or data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Candy
    -0.07
    ============
    -0.07
     حرکت
    -0.07
    	timeout
    -0.06
    ollo
    -0.06
     svém
    -0.06
     projectName
    -0.06
     salope
    -0.06
    ��
    -0.06
     lot
    -0.06
    POSITIVE LOGITS
    ेत
    0.07
    дер
    0.07
    ptions
    0.06
     Journalism
    0.06
    cle
    0.06
    AGING
    0.06
    ims
    0.06
    MESS
    0.06
    END
    0.06
    enschaft
    0.06
    Act Density 0.000%

    No Known Activations