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

    Neuronpedia

    INDEX
    Explanations

    mentions, states, and about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Очень
    0.47
    п
    0.45
    ᓄ
    0.43
    ógicos
    0.40
    ilina
    0.40
    ፩
    0.40
    óricos
    0.40
    omon
    0.40
    ци
    0.40
     типи
    0.40
    POSITIVE LOGITS
     aforementioned
    0.51
     llamar
    0.48
     sich
    0.47
     hace
    0.46
     cambia
    0.46
     اینکه
    0.46
     the
    0.44
     mentioned
    0.44
     pesky
    0.44
     der
    0.44
    Act Density 0.109%

    No Known Activations