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

    Neuronpedia

    INDEX
    Explanations

    possessive pronoun plus "lips"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jonas
    0.39
    ငန်း
    0.39
     franchisees
    0.38
    ندوق
    0.37
    aldo
    0.37
     finance
    0.36
    稼
    0.35
     आनंद
    0.35
    વણી
    0.35
     डैश
    0.35
    POSITIVE LOGITS
     lips
    3.44
     lip
    3.27
     Lips
    2.95
    Lip
    2.88
     Lip
    2.86
    lips
    2.84
    唇
    2.84
    Lips
    2.81
    lip
    2.69
     lèvres
    2.39
    Act Density 0.027%

    No Known Activations