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

    Neuronpedia

    INDEX
    Explanations

    details

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ป
    -0.07
    �
    -0.07
     تق
    -0.07
     suchen
    -0.07
    .localScale
    -0.07
    داف
    -0.06
    洇
    -0.06
    专班
    -0.06
    了几
    -0.06
    achment
    -0.06
    POSITIVE LOGITS
    /Library
    0.08
    Mexico
    0.07
    Filled
    0.07
    Listing
    0.07
     Lester
    0.07
    -shell
    0.07
    реш
    0.07
     chất
    0.07
    ="'.
    0.07
     LM
    0.07
    Act Density 0.001%

    No Known Activations