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

    Neuronpedia

    INDEX
    Explanations

    blocks of documentation comments in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code and non-English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    -0.53
    ❤❤
    -0.43
    ally
    -0.42
    ly
    -0.42
    [
    -0.40
    a
    -0.39
     Administrativna
    -0.39
    깥
    -0.38
    =
    -0.38
    ({
    -0.37
    POSITIVE LOGITS
    Pozdrawiam
    0.62
    newBuilder
    0.59
     DCM
    0.52
     JMS
    0.52
    iería
    0.50
    jaardag
    0.50
     Cheltenham
    0.50
     betweenstory
    0.49
     springfox
    0.49
    digarh
    0.49
    Act Density 0.020%

    No Known Activations