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

    Neuronpedia

    INDEX
    Explanations

    code, logs, technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wins
    -0.07
    \Route
    -0.06
    걸
    -0.06
    hunt
    -0.06
     rekl
    -0.06
     //'
    -0.06
    まる
    -0.06
    uya
    -0.06
     찬
    -0.06
     Girlfriend
    -0.06
    POSITIVE LOGITS
    ponsored
    0.06
     ；
    0.06
     organisms
    0.06
    qual
    0.06
    خص
    0.06
     auditing
    0.06
    efficient
    0.06
    Before
    0.06
     memory
    0.06
     grazing
    0.06
    Act Density 0.000%

    No Known Activations