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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Nd
    -0.06
    ,Integer
    -0.06
     Ded
    -0.06
    _shape
    -0.06
    markdown
    -0.06
    auf
    -0.06
     bào
    -0.06
    82
    -0.06
    .cn
    -0.06
     ค
    -0.06
    POSITIVE LOGITS
     fix
    0.07
     try
    0.07
    	Use
    0.07
    !")↵
    0.07
     nouvelle
    0.06
    器
    0.06
    하자
    0.06
     Cannabis
    0.06
     خاطر
    0.06
     �
    0.06
    Act Density 0.088%

    No Known Activations