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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ď
    -0.07
    _TOOL
    -0.07
    .security
    -0.07
    .study
    -0.07
     Rodrig
    -0.07
     Porto
    -0.06
    مرك
    -0.06
    耽误
    -0.06
     EDT
    -0.06
    뺐
    -0.06
    POSITIVE LOGITS
    _cc
    0.07
    ({})↵
    0.07
    一向
    0.07
    	line
    0.07
     var
    0.07
    sprites
    0.06
     crear
    0.06
     partners
    0.06
    aseline
    0.06
    inese
    0.06
    Act Density 0.001%

    No Known Activations