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

    Neuronpedia

    INDEX
    Explanations

    Quotation/equals signs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     metabol
    -0.08
    畖
    -0.08
     kd
    -0.07
    TM
    -0.07
    𬣳
    -0.07
     lp
    -0.07
     }
↵
    -0.07
     CHANGE
    -0.06
     tích
    -0.06
    סטוד
    -0.06
    POSITIVE LOGITS
    .Platform
    0.08
    صوم
    0.07
     objet
    0.07
     Outdoor
    0.07
    היינו
    0.07
    くなる
    0.07
    ->$
    0.07
    랐
    0.07
    scrollTop
    0.07
    お客
    0.07
    Act Density 0.033%

    No Known Activations