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

    Neuronpedia

    INDEX
    Explanations

    support

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    currently
    -0.08
    -0.07
     mất
    -0.07
    ಐ
    -0.07
    �
    -0.07
    [];↵
    -0.06
    /chart
    -0.06
     categorie
    -0.06
     programma
    -0.06
    懿
    -0.06
    POSITIVE LOGITS
     بالن
    0.08
    نغ
    0.08
    攀登
    0.08
     наб
    0.07
     grips
    0.07
     główna
    0.07
    原始
    0.07
    还不是
    0.07
     stronger
    0.07
    Trim
    0.07
    Act Density 0.054%

    No Known Activations