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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sciences
    -0.06
    АН
    -0.06
    ğan
    -0.06
    "])
    -0.06
    욱
    -0.06
    ební
    -0.06
    HttpClient
    -0.06
    .provider
    -0.06
     ikinci
    -0.06
    :eq
    -0.06
    POSITIVE LOGITS
     replay
    0.08
     Illustrator
    0.07
     تأثیر
    0.07
    ापक
    0.06
     tolerated
    0.06
     conditioned
    0.06
    	redirect
    0.06
     ”↵↵
    0.06
     drib
    0.06
    olulu
    0.06
    Act Density 0.040%

    No Known Activations