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

    Neuronpedia

    INDEX
    Explanations

    names and technical identifiers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    に適
    0.55
    isco
    0.55
    Graph
    0.54
    atschapp
    0.54
    볕
    0.53
    wechsel
    0.53
    schild
    0.52
    erti
    0.51
     asignar
    0.51
    oucher
    0.51
    POSITIVE LOGITS
    檴
    0.57
     intimate
    0.57
     precipitated
    0.57
     scares
    0.55
     مرور
    0.55
     완전
    0.54
     full
    0.54
     mów
    0.54
     സമ്പ
    0.54
     полного
    0.53
    Act Density 0.001%

    No Known Activations