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

    Neuronpedia

    INDEX
    Explanations

    private sessions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indeterminate
    0.68
     Allende
    0.66
    པ
    0.65
     Paleo
    0.64
    धे
    0.64
     diverging
    0.64
    ofSeconds
    0.63
     🙂
    0.63
     wonderful
    0.62
    сля
    0.62
    POSITIVE LOGITS
     rappers
    1.67
     rap
    1.61
     rapping
    1.61
     rapper
    1.56
     hip
    1.29
     nigga
    1.27
     dope
    1.27
     Rap
    1.25
     Hip
    1.24
    Hip
    1.20
    Act Density 0.370%

    No Known Activations