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

    Neuronpedia

    INDEX
    Explanations

    journal volume citation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     térmica
    0.34
     araç
    0.33
    ခြား
    0.33
    ಿಸುತ್ತದೆ
    0.32
     étab
    0.31
    arrerol
    0.31
     véhicule
    0.31
    ဉ်
    0.31
    eping
    0.31
    শকা
    0.31
    POSITIVE LOGITS
     Volume
    0.91
     Vol
    0.88
    Volume
    0.84
     volume
    0.80
     vol
    0.79
    volume
    0.79
    Vol
    0.75
     VOLUME
    0.73
     volumen
    0.69
     Volumes
    0.68
    Act Density 0.001%

    No Known Activations