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

    Neuronpedia

    INDEX
    Explanations

    UI elements

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Michelin
    0.57
     intestinal
    0.56
     Josephson
    0.56
     पाया
    0.56
     decals
    0.55
    广东省
    0.55
     धाराओं
    0.55
     checkboxes
    0.55
     streamline
    0.54
     macaroni
    0.54
    POSITIVE LOGITS
    lz
    0.73
    lg
    0.63
    lbl
    0.61
    lf
    0.59
    lk
    0.59
    UMN
    0.59
    LZ
    0.59
    alem
    0.59
    lw
    0.58
    lv
    0.58
    Act Density 0.001%

    No Known Activations