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

    Neuronpedia

    INDEX
    Explanations

    kinds of creative text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ChatGPT
    0.42
     ulcers
    0.41
     econometric
    0.40
     sarcom
    0.39
     moldings
    0.39
     suites
    0.37
     closets
    0.37
     cirrhosis
    0.37
     नौकर
    0.36
     ChatGPT
    0.36
    POSITIVE LOGITS
    ine
    0.41
    rit
    0.39
    akin
    0.38
     Images
    0.38
    av
    0.38
    ewhat
    0.37
     Questions
    0.37
    atown
    0.37
     Struggles
    0.37
    here
    0.36
    Act Density 0.274%

    No Known Activations