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

    Neuronpedia

    INDEX
    Explanations

    General purpose text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etroit
    -0.07
    >No
    -0.07
    /embed
    -0.07
     sle
    -0.06
     cí
    -0.06
     aure
    -0.06
    SAFE
    -0.06
    撰
    -0.06
     fik
    -0.06
     شعر
    -0.06
    POSITIVE LOGITS
     Washer
    0.07
     attn
    0.06
    entry
    0.06
     Bliss
    0.06
    �
    0.06
     '/');↵
    0.06
     ثلاث
    0.06
    胞
    0.06
    000
    0.06
    *dt
    0.06
    Act Density 0.000%

    No Known Activations