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

    Neuronpedia

    INDEX
    Explanations

    source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    孕妇
    -0.08
     Managers
    -0.08
    Decrypt
    -0.07
     predicates
    -0.07
    _episodes
    -0.07
     graduating
    -0.07
    انتخاب
    -0.07
    伭
    -0.07
     VARIABLES
    -0.07
     flirt
    -0.06
    POSITIVE LOGITS
    ution
    0.07
    Ҫ
    0.07
    taş
    0.07
    	sb
    0.07
     nameLabel
    0.07
    çi
    0.07
    舌尖
    0.07
    ак
    0.07
    .hd
    0.07
     volver
    0.07
    Act Density 0.084%

    No Known Activations