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

    Neuronpedia

    INDEX
    Explanations

    evidence or proof

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    leszt
    0.71
     workpiece
    0.68
    Traversal
    0.68
     chantier
    0.68
     openai
    0.67
    ractive
    0.67
     XMFLOAT
    0.66
     нажа
    0.66
    ("|"+"
    0.65
    夢
    0.64
    POSITIVE LOGITS
     evidence
    2.86
     Evidence
    2.54
    证据
    2.53
    Evidence
    2.47
    evidence
    2.43
     proof
    2.36
    證據
    2.36
     EVIDENCE
    2.33
     доказа
    2.24
     evidences
    2.15
    Act Density 1.745%

    No Known Activations