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

    Neuronpedia

    INDEX
    Explanations

    unique or specific aspects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _NR
    -0.29
    ILLED
    -0.27
    agli
    -0.26
    ä¸ĵéŨ
    -0.26
    allas
    -0.26
    æĬ¤åį«
    -0.25
     force
    -0.25
    енной
    -0.24
     forces
    -0.24
    _border
    -0.24
    POSITIVE LOGITS
    èĨ
    0.32
    æĪijä¸įæĺ¯
    0.30
    [:,:,
    0.25
    insky
    0.25
    .rs
    0.24
    Soft
    0.24
     collaborators
    0.24
    iego
    0.24
    çįIJ
    0.23
    .requireNonNull
    0.23
    Act Density 0.002%

    No Known Activations