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

    Neuronpedia

    INDEX
    Explanations

    area and dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     protobuf
    0.66
     dispersions
    0.61
    HEX
    0.60
    Largest
    0.59
     Controversy
    0.58
    ഗ്രഹം
    0.57
    湟
    0.56
     lakh
    0.56
     fief
    0.55
    طلح
    0.55
    POSITIVE LOGITS
     drafting
    0.68
     pendekatan
    0.62
     sicuramente
    0.61
     davvero
    0.60
    {
    0.58
     stratégies
    0.58
     opravdu
    0.57
     confirmé
    0.56
    勾
    0.55
     confirm
    0.55
    Act Density 0.000%

    No Known Activations