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

    Neuronpedia

    INDEX
    Explanations

    felon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acd
    -0.07
     ไป
    -0.06
    izza
    -0.06
     Hatch
    -0.06
     instability
    -0.06
     NodeType
    -0.06
     explanatory
    -0.06
     Cush
    -0.06
    ائ
    -0.06
    ์แ
    -0.06
    POSITIVE LOGITS
     felon
    0.07
    ोच
    0.06
    mon
    0.06
     malaysia
    0.06
    ===
    0.06
    ikan
    0.06
     man
    0.06
    -result
    0.06
    兵
    0.06
    oen
    0.06
    Act Density 0.001%

    No Known Activations