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

    Neuronpedia

    INDEX
    Explanations

    making things to predict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     opciones
    0.47
     basura
    0.47
     hipster
    0.46
     PUBG
    0.46
     principales
    0.45
     unmittel
    0.44
     AirPods
    0.44
     hostels
    0.44
     interdit
    0.44
     simpat
    0.43
    POSITIVE LOGITS
    ARY
    0.46
     יה
    0.45
    彤
    0.45
    Terry
    0.42
    istered
    0.42
    ight
    0.42
    יה
    0.42
    oski
    0.42
    itt
    0.42
    ructive
    0.42
    Act Density 0.001%

    No Known Activations