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

    Neuronpedia

    INDEX
    Explanations

    ^

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erras
    -0.07
     mafia
    -0.07
     airplane
    -0.06
     signs
    -0.06
    ARRAY
    -0.06
    迹
    -0.06
     murdered
    -0.06
     bại
    -0.06
    _profiles
    -0.06
     sunlight
    -0.06
    POSITIVE LOGITS
    タイ
    0.07
     �
    0.07
     CVE
    0.07
     "~
    0.06
     ettiği
    0.06
    знача
    0.06
     precedence
    0.06
     nghĩa
    0.06
     Gender
    0.06
    cap
    0.06
    Act Density 0.002%

    No Known Activations