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

    Neuronpedia

    INDEX
    Explanations

    immediate actions instructing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }:\
    0.78
    :\
    0.73
    }:
    0.70
    ിക്കുകയും
    0.66
    :";
    0.65
    :");
    0.65
    :}
    0.64
    िके
    0.64
    :</
    0.60
    :")
    0.60
    POSITIVE LOGITS
     nulla
    0.82
     niente
    0.81
     behem
    0.78
     questo
    0.77
     berikut
    0.72
     enterprises
    0.71
     awalnya
    0.69
     toate
    0.69
    ↵↵
    0.69
     enterprise
    0.68
    Act Density 0.794%

    No Known Activations