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
    stress
    -0.07
    _arc
    -0.07
    ライブ
    -0.07
    (Parse
    -0.07
     treffen
    -0.07
     }↵↵↵↵
    -0.07
    악
    -0.07
    supported
    -0.07
     Freeman
    -0.06
     cô
    -0.06
    POSITIVE LOGITS
    濞
    0.08
    תשובות
    0.08
    ww
    0.07
    JsonProperty
    0.07
    SenderId
    0.07
    alary
    0.07
    叫
    0.07
     Más
    0.07
     משפ
    0.07
     Mediterr
    0.07
    Act Density 0.003%

    No Known Activations