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

    Neuronpedia

    INDEX
    Explanations

    read

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “read” or complaints about being able to read text (i.e. readability concerns).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    验证
    -0.07
    .logo
    -0.07
     frase
    -0.06
    Disc
    -0.06
    progressbar
    -0.06
    .blog
    -0.06
     jours
    -0.06
    pants
    -0.06
     FA
    -0.06
     PackageManager
    -0.06
    POSITIVE LOGITS
     SignUp
    0.07
     topLevel
    0.06
    neğin
    0.06
    二二
    0.06
    cripcion
    0.06
    	pthread
    0.06
    leftright
    0.06
    Drivers
    0.06
    atherine
    0.06
    zh
    0.06
    Act Density 0.021%

    No Known Activations