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

    Neuronpedia

    INDEX
    Explanations

    Is it a word?

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TICK
    -0.07
    _MT
    -0.07
    _POL
    -0.06
     bases
    -0.06
    텔
    -0.06
     bone
    -0.06
     male
    -0.06
    Persons
    -0.06
    oyo
    -0.06
     Rough
    -0.06
    POSITIVE LOGITS
     cré
    0.07
    <Player
    0.07
     تهران
    0.06
     зменш
    0.06
     debris
    0.06
     });
↵
    0.06
    됩니다
    0.06
     Harness
    0.06
    術
    0.06
     assignable
    0.06
    Act Density 0.016%

    No Known Activations