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

    Neuronpedia

    INDEX
    Explanations

    website or code editing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     управления
    -0.07
    addItem
    -0.07
     download
    -0.07
    맹
    -0.07
    길
    -0.07
    .assertAlmostEqual
    -0.07
    aporation
    -0.07
    _agg
    -0.06
    ethylene
    -0.06
     употреб
    -0.06
    POSITIVE LOGITS
    });↵↵
    0.06
    997
    0.06
     kk
    0.06
     TN
    0.06
     کردم
    0.06
     prevent
    0.06
     Snape
    0.05
    .Character
    0.05
     Bunny
    0.05
     parm
    0.05
    Act Density 0.018%

    No Known Activations