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

    Neuronpedia

    INDEX
    Explanations

    Code snippets/technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     материалов
    -0.07
    アップ
    -0.07
    omer
    -0.07
    Writes
    -0.07
    تاب
    -0.06
     vant
    -0.06
    (cps
    -0.06
     vezes
    -0.06
     nunca
    -0.06
    }//
    -0.06
    POSITIVE LOGITS
    appeared
    0.07
     +/-
    0.06
     Given
    0.06
     British
    0.06
     와
    0.06
     Enhanced
    0.06
     These
    0.06
     fed
    0.06
     purple
    0.06
    -binding
    0.06
    Act Density 0.000%

    No Known Activations