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

    Neuronpedia

    INDEX
    Explanations

    created

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     музык
    -0.08
    ّ
    -0.07
    кар
    -0.07
    oons
    -0.07
    罂
    -0.07
     Bod
    -0.07
     Campos
    -0.07
    校外
    -0.07
     jul
    -0.07
    ucs
    -0.07
    POSITIVE LOGITS
     monitoring
    0.07
    .isTrue
    0.07
    --;↵
    0.07
    -import
    0.07
    >';↵
    0.07
    					↵
    0.06
    =["
    0.06
    .visibility
    0.06
    iglia
    0.06
    四项
    0.06
    Act Density 0.000%

    No Known Activations