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

    Neuronpedia

    INDEX
    Explanations

    identity and security terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᡳ
    0.38
     nok
    0.38
    𝓾
    0.38
    volved
    0.37
     slimy
    0.37
    soaked
    0.37
     ,"
    0.37
     ins
    0.36
    ,]
    0.36
    token
    0.36
    POSITIVE LOGITS
     identidad
    0.55
     иденти
    0.55
     identity
    0.48
     идентифика
    0.48
     Identity
    0.47
     ID
    0.46
    setId
    0.45
     identifications
    0.45
     आईडी
    0.44
     IDENTITY
    0.43
    Act Density 0.010%

    No Known Activations