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

    Neuronpedia

    INDEX
    Explanations

    key derivation and salts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alde
    0.47
    介绍
    0.46
    certificate
    0.46
    签名
    0.40
     डिजिटल
    0.38
     certificados
    0.38
     códigos
    0.38
    certificates
    0.38
    differential
    0.38
    ब्रे
    0.38
    POSITIVE LOGITS
     salt
    0.63
     derivation
    0.59
     derive
    0.57
     Derive
    0.57
     Salt
    0.54
     derived
    0.53
     Der
    0.52
     salts
    0.52
     derives
    0.49
    Salt
    0.49
    Act Density 0.037%

    No Known Activations