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

    Neuronpedia

    INDEX
    Explanations

    evidence and proof

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ন্যবাদ
    0.76
     पॉलिटी
    0.64
     assuntos
    0.63
    转载
    0.62
    ानीय
    0.62
    畅
    0.62
    isPartOf
    0.61
    optimizers
    0.61
    Chào
    0.60
    Translator
    0.60
    POSITIVE LOGITS
     evidence
    4.44
     Evidence
    3.97
    evidence
    3.89
    Evidence
    3.89
     proof
    3.88
    证据
    3.64
     EVIDENCE
    3.53
     evidences
    3.48
     Proof
    3.42
    證據
    3.36
    Act Density 0.328%

    No Known Activations