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

    Neuronpedia

    INDEX
    Explanations

    model response phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shrinks
    0.65
     গ্রস্থ
    0.63
     Riggs
    0.60
     buf
    0.60
     shrink
    0.59
     LPTMR
    0.58
     unsaturated
    0.58
     careg
    0.58
    berat
    0.57
    buf
    0.57
    POSITIVE LOGITS
    oc
    0.67
    ok
    0.66
     حاضر
    0.62
     সাং
    0.61
    OC
    0.61
     OC
    0.59
    OCI
    0.57
     pe
    0.56
    Setup
    0.55
    Disc
    0.55
    Act Density 0.214%

    No Known Activations