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

    Neuronpedia

    INDEX
    Explanations

    News snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    41
    -0.06
    ород
    -0.06
    .addField
    -0.06
     damage
    -0.06
    ("").
    -0.06
    _sparse
    -0.06
     heavily
    -0.06
     Conservative
    -0.06
    ]).↵
    -0.05
    mapped
    -0.05
    POSITIVE LOGITS
    /tab
    0.07
    efs
    0.07
     kInstruction
    0.06
    _CFG
    0.06
    ὰ
    0.06
     comparisons
    0.06
    дя
    0.06
    луб
    0.06
     Physiology
    0.06
    \TestCase
    0.06
    Act Density 0.266%

    No Known Activations