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

    Neuronpedia

    INDEX
    Explanations

    perhaps offer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entrando
    0.45
    anaf
    0.42
    كة
    0.42
    ళ్లు
    0.42
    醬
    0.42
    Therates
    0.41
     অন্
    0.41
    ▦
    0.40
     කෙ
    0.40
    щен
    0.39
    POSITIVE LOGITS
     And
    0.43
     Exhibit
    0.41
     perhaps
    0.39
     निम्न
    0.38
    charg
    0.37
     but
    0.37
     Chargers
    0.37
     possibly
    0.36
     conscient
    0.36
     以下
    0.36
    Act Density 0.000%

    No Known Activations