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

    Neuronpedia

    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Officials
    -0.07
    Extras
    -0.06
     pi
    -0.06
    _na
    -0.06
     Snackbar
    -0.06
     pref
    -0.06
    ίο
    -0.06
     algunos
    -0.06
     adresse
    -0.06
     rele
    -0.06
    POSITIVE LOGITS
     Rupert
    0.15
    upert
    0.10
    alchemy
    0.09
    jdk
    0.09
    @Setter
    0.07
     gratitude
    0.06
     Edmund
    0.06
     Stars
    0.06
     Engineers
    0.06
     культу
    0.06
    Act Density 0.002%

    No Known Activations