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

    Neuronpedia

    INDEX
    Explanations

    approval ratings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     derivative
    0.41
    Derivative
    0.37
     Derivative
    0.37
    GCC
    0.37
     транспо
    0.36
     annotation
    0.35
     setIs
    0.35
     deriva
    0.34
     inz
    0.34
     transporter
    0.33
    POSITIVE LOGITS
    कता
    0.43
    issanti
    0.41
    ाये
    0.39
    Categ
    0.38
    ന്റി
    0.38
     Defts
    0.38
    活跃
    0.37
     For
    0.37
    rv
    0.37
    0.37
    Act Density 0.000%

    No Known Activations