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

    Neuronpedia

    INDEX
    Explanations

    online math or AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     subject
    0.68
     approaching
    0.67
     estr
    0.65
     topic
    0.65
     предпо
    0.65
     appeared
    0.64
     persistent
    0.64
     appear
    0.64
     predisposition
    0.64
     appears
    0.63
    POSITIVE LOGITS
    PIP
    0.95
     Psp
    0.83
    PP
    0.81
    PSP
    0.79
    PAP
    0.77
    PPS
    0.77
    hnten
    0.75
    cPix
    0.74
     idP
    0.74
    itted
    0.73
    Act Density 0.374%

    No Known Activations