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

    Neuronpedia

    INDEX
    Explanations

    explanations and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒄯
    1.82
    𒀫
    1.73
     battleF
    1.72
    abeledtr
    1.72
    𒀮
    1.72
    SRPCS
    1.71
    𒀩
    1.71
    𒊖
    1.71
    ꗓ
    1.71
    𒄾
    1.70
    POSITIVE LOGITS
    ↵↵
    2.75
    ↵
    2.30
    ↵↵↵
    1.80
    ↵↵↵↵
    1.52
    ↵↵↵↵↵
    1.24
    <h2>
    1.10
    ↵↵↵↵↵↵
    1.01
    <start_of_image>
    0.97
      
    0.97
     The
    0.92
    Act Density 0.584%

    No Known Activations