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

    Neuronpedia

    INDEX
    Explanations

    profile or profit details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nen
    0.49
    ish
    0.48
    sol
    0.48
    ject
    0.46
    s
    0.45
    course
    0.44
    service
    0.44
    я
    0.43
    signed
    0.43
    на
    0.43
    POSITIVE LOGITS
     prof
    0.71
     проф
    0.66
     profil
    0.63
    Profil
    0.62
     پروف
    0.60
     Profil
    0.58
     profiles
    0.56
     profite
    0.55
    Prof
    0.55
     PROF
    0.52
    Act Density 0.010%

    No Known Activations