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

    Neuronpedia

    INDEX
    Explanations

    miscellaneous texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     immun
    -0.07
     Dwarf
    -0.07
    种类
    -0.07
    🅻
    -0.07
     cấp
    -0.07
     Provided
    -0.06
    .xrLabel
    -0.06
     Infragistics
    -0.06
     Navigate
    -0.06
    ភ
    -0.06
    POSITIVE LOGITS
    0.07
    Курс
    0.07
    usp
    0.07
     reordered
    0.07
     subconscious
    0.07
     grandchildren
    0.07
           
    0.07
    	org
    0.07
    	Y
    0.07
    缠
    0.07
    Act Density 0.418%

    No Known Activations