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

    Neuronpedia

    INDEX
    Explanations

    software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     forc
    -0.07
     grouping
    -0.07
     dive
    -0.07
    менш
    -0.07
     RTS
    -0.07
     quat
    -0.06
     �
    -0.06
     satur
    -0.06
    _encode
    -0.06
    POSITIVE LOGITS
    Pool
    0.06
    getPost
    0.06
    (Sub
    0.06
    LB
    0.06
    584
    0.06
    latex
    0.06
    	back
    0.06
    lobal
    0.06
    Initializer
    0.05
    fé
    0.05
    Act Density 0.116%

    No Known Activations