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

    Neuronpedia

    INDEX
    Explanations

    On Tick

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yesha
    0.79
    Ontario
    0.75
     Ontario
    0.75
     Wisconsin
    0.75
     Baseball
    0.74
     मुंबई
    0.74
    ိုင်း
    0.74
     Allegheny
    0.73
     pitcher
    0.73
    ahraga
    0.72
    POSITIVE LOGITS
    Ко
    1.48
    По
    1.47
    С
    1.45
    俄罗斯
    1.44
    Т
    1.39
    Ва
    1.39
    К
    1.37
    Не
    1.36
     А
    1.36
    Coef
    1.34
    Act Density 0.079%

    No Known Activations