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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CONV
    -0.07
     bewild
    -0.06
     Amelia
    -0.06
     Sele
    -0.06
    titles
    -0.06
    یز
    -0.06
     каз
    -0.06
    етод
    -0.06
     xuyên
    -0.06
    setup
    -0.06
    POSITIVE LOGITS
     iken
    0.06
    mtime
    0.06
     besides
    0.06
    	HashMap
    0.06
    _STAT
    0.06
    /REC
    0.06
     освещ
    0.06
    шая
    0.06
     gunfire
    0.06
    RV
    0.06
    Act Density 0.121%

    No Known Activations