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

    Neuronpedia

    INDEX
    Explanations

    science, technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    也同样
    -0.07
    angelo
    -0.07
    どんどん
    -0.07
     Inv
    -0.07
    にも
    -0.07
    守住
    -0.07
    何度も
    -0.07
    法则
    -0.07
    .asp
    -0.07
    不动
    -0.07
    POSITIVE LOGITS
    _SUS
    0.06
     favourite
    0.06
    _B
    0.06
    0.06
    �
    0.06
    _SAN
    0.06
    GRE
    0.06
    祭祀
    0.06
    //↵↵↵
    0.06
     término
    0.06
    Act Density 0.097%

    No Known Activations