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

    Neuronpedia

    INDEX
    Explanations

    geared towards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Branch
    0.83
    ем
    0.81
    ki
    0.81
     quantifying
    0.80
     quantify
    0.80
     bounds
    0.77
    आधार
    0.77
    上の
    0.75
     correlated
    0.74
     passwords
    0.74
    POSITIVE LOGITS
     towards
    2.76
     toward
    2.50
     Towards
    2.44
    towards
    2.38
    Towards
    2.30
     Toward
    2.23
    Toward
    2.04
     hacia
    2.03
     نحو
    1.64
     отношению
    1.46
    Act Density 0.113%

    No Known Activations