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

    Neuronpedia

    INDEX
    Explanations

    class MyCustomDefinition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    িকাল
    0.41
     ajuns
    0.38
    ධා
    0.37
    ualmente
    0.36
     toepassing
    0.36
    ostino
    0.36
    asso
    0.35
     дом
    0.35
    ⚜
    0.35
     actuellement
    0.35
    POSITIVE LOGITS
    My
    0.95
     My
    0.93
     my
    0.90
     Custom
    0.88
    Custom
    0.84
     MY
    0.82
     custom
    0.80
    my
    0.78
    custom
    0.70
    我的
    0.68
    Act Density 0.012%

    No Known Activations