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

    Neuronpedia

    INDEX
    Explanations

    official organizations and agencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ub
    0.46
    ot
    0.45
    ensure
    0.43
    but
    0.42
     それ
    0.42
    int
    0.41
    ab
    0.39
    os
    0.39
    DataFrame
    0.39
    SCs
    0.39
    POSITIVE LOGITS
     Reverend
    0.40
     Asw
    0.39
     Jeep
    0.38
     Sasha
    0.38
     země
    0.38
     extremist
    0.38
     Javier
    0.37
     fourn
    0.36
     Saty
    0.36
     clasific
    0.36
    Act Density 0.009%

    No Known Activations