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

    Neuronpedia

    INDEX
    Explanations

    ear, mask, head components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suspicion
    0.67
     Denison
    0.67
     speculation
    0.62
     pilgrimage
    0.60
     Pilgr
    0.59
     kaufen
    0.59
     webinar
    0.58
     ansatz
    0.58
     Webinar
    0.57
     servitude
    0.57
    POSITIVE LOGITS
     gây
    0.62
    grade
    0.57
    grades
    0.56
     rude
    0.55
     gent
    0.55
     établir
    0.54
     இடத்தை
    0.52
     grades
    0.52
    Gent
    0.51
     tercer
    0.51
    Act Density 0.000%

    No Known Activations