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

    Neuronpedia

    INDEX
    Explanations

    case

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geschrieben
    0.79
    falen
    0.78
    abajo
    0.76
    ுகிற
    0.71
    lower
    0.70
    Buongiorno
    0.70
    elaar
    0.70
    ക്കാല
    0.70
     لکھا
    0.69
    倝
    0.69
    POSITIVE LOGITS
     sensitive
    0.77
     sensitivity
    0.73
     Sensitivity
    0.73
     awareness
    0.73
     Varn
    0.69
     cogniz
    0.69
     sensitivities
    0.68
     Sensitive
    0.66
     Aware
    0.65
     Awareness
    0.64
    Act Density 0.007%

    No Known Activations