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

    Neuronpedia

    INDEX
    Explanations

    State

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     evac
    -0.08
    pires
    -0.07
     mét
    -0.07
    contrib
    -0.07
     insn
    -0.07
    _Mod
    -0.07
     зая
    -0.07
    .ipv
    -0.07
     stake
    -0.06
     souha
    -0.06
    POSITIVE LOGITS
    .Sound
    0.08
    (actual
    0.08
    涠
    0.07
    يري
    0.07
    bung
    0.07
    수가
    0.07
    蟛
    0.07
    圆形
    0.07
     typography
    0.06
    lük
    0.06
    Act Density 0.003%

    No Known Activations