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

    Neuronpedia

    INDEX
    Explanations

    prisoner

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    歲
    -0.08
    ⟨
    -0.07
     반드시
    -0.07
    f
    -0.07
    abyrinth
    -0.07
    iphery
    -0.07
    ရ
    -0.07
     ><
    -0.06
    ⌥
    -0.06
    赶
    -0.06
    POSITIVE LOGITS
     prisoners
    0.07
    _Model
    0.07
    申请
    0.07
     Lista
    0.07
    iVar
    0.07
    _inline
    0.07
    韫
    0.07
    _InitStruct
    0.07
    まと
    0.07
    אוניב
    0.07
    Act Density 0.004%

    No Known Activations