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

    Neuronpedia

    INDEX
    Explanations

    synthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     meine
    -0.08
     optional
    -0.07
    .perform
    -0.07
     Proc
    -0.07
    골
    -0.07
    讯
    -0.07
     médico
    -0.07
    奖学金
    -0.06
     mood
    -0.06
    (DEBUG
    -0.06
    POSITIVE LOGITS
     evil
    0.08
    化身
    0.07
    Compatibility
    0.07
    раб
    0.07
    Animator
    0.07
    하자
    0.06
     Trilogy
    0.06
     convention
    0.06
     Grave
    0.06
    ()")↵
    0.06
    Act Density 0.039%

    No Known Activations