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

    Neuronpedia

    INDEX
    Explanations

    Listeria

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     $('[
    -0.07
    有这样的
    -0.07
    湘潭
    -0.07
    ➵
    -0.07
    出资
    -0.07
     Chuck
    -0.06
    ཙ
    -0.06
    ⛪
    -0.06
     товар
    -0.06
     licensors
    -0.06
    POSITIVE LOGITS
     Serbia
    0.08
     ly
    0.08
    Ń
    0.08
     열
    0.08
     mixing
    0.07
    肾脏
    0.07
    蘑
    0.07
    Debug
    0.07
    しても
    0.07
    表演
    0.07
    Act Density 0.001%

    No Known Activations