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

    Neuronpedia

    INDEX
    Explanations

    Service configuration or closure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    り
    1.31
    вання
    1.14
    нут
    1.11
    ব
    1.11
    いた
    1.07
    tedir
    1.07
    いますが
    1.07
    quoi
    1.06
    います
    1.05
    ل
    1.05
    POSITIVE LOGITS
     dispar
    0.85
     belie
    0.82
     %%
    0.82
     OZ
    0.82
     DIS
    0.79
     archae
    0.77
     ○
    0.76
     greenhouse
    0.74
     gg
    0.73
     ruth
    0.73
    Act Density 0.002%

    No Known Activations