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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alexa
    -0.08
     sprintf
    -0.08
    -backend
    -0.07
    .www
    -0.07
    (document
    -0.06
    られる
    -0.06
    $headers
    -0.06
    	operator
    -0.06
     assets
    -0.06
     شماره
    -0.06
    POSITIVE LOGITS
     PodsDummy
    0.07
    psi
    0.06
     푸
    0.06
    λη
    0.06
     Dolphins
    0.05
    hpp
    0.05
    difference
    0.05
    William
    0.05
    ротив
    0.05
    �
    0.05
    Act Density 0.030%

    No Known Activations