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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    0.89
    Aber
    0.84
    Что
    0.82
    в
    0.81
    Having
    0.80
    ी
    0.80
    ти
    0.78
    Neue
    0.78
    While
    0.76
    ہ
    0.75
    POSITIVE LOGITS
     kilow
    1.00
     idempotent
    1.00
     walnuts
    0.99
     doxycycline
    0.96
     aerosols
    0.96
    ﺧ
    0.96
     postural
    0.95
     vacuoles
    0.95
     aerosol
    0.92
     KGB
    0.91
    Act Density 0.000%

    No Known Activations