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

    Neuronpedia

    INDEX
    Explanations

    base64 encoded images

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     Switch
    -0.07
    衒
    -0.07
     Sylvia
    -0.07
    �
    -0.07
     tweaks
    -0.07
    ᥱ
    -0.07
     tern
    -0.07
     cancelButtonTitle
    -0.07
    彖
    -0.07
    POSITIVE LOGITS
    之战
    0.07
    🔞
    0.07
    =./
    0.07
     Blood
    0.07
     Rum
    0.07
    问答
    0.07
    对方
    0.07
    ASCADE
    0.07
     parallel
    0.07
     External
    0.07
    Act Density 0.005%

    No Known Activations