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

    Neuronpedia

    INDEX
    Explanations

    center

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spender
    -0.07
    大家都在
    -0.07
     scouting
    -0.07
    ﯤ
    -0.07
    力还是自
    -0.07
     banner
    -0.06
     HEADER
    -0.06
     Kahn
    -0.06
    \Service
    -0.06
     Fall
    -0.06
    POSITIVE LOGITS
    ować
    0.07
    zig
    0.07
    迳
    0.07
    edis
    0.06
    gü
    0.06
    Modificar
    0.06
    蟑
    0.06
    عرف
    0.06
    į
    0.06
    גישה
    0.06
    Act Density 0.006%

    No Known Activations