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

    Neuronpedia

    INDEX
    Explanations

    previous step or context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⑶
    0.43
    ⑸
    0.42
    Lynn
    0.42
    gdf
    0.40
     Cobra
    0.40
     String
    0.39
     až
    0.38
     string
    0.37
     Travis
    0.36
    string
    0.36
    POSITIVE LOGITS
    िक
    0.48
    的其他
    0.45
    ieurs
    0.42
     DIFFERENT
    0.41
    iertas
    0.40
    entliche
    0.40
    ामध्ये
    0.40
     BOTH
    0.40
     chrét
    0.40
     Tribun
    0.40
    Act Density 0.007%

    No Known Activations