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

    Neuronpedia

    INDEX
    Explanations

    references to signs and their usage

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

    signs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fletcher
    -0.60
     Hara
    -0.54
     Cabral
    -0.54
    Халык
    -0.52
    期刊论文
    -0.52
    amba
    -0.51
    rdata
    -0.50
    retto
    -0.50
     sparingly
    -0.50
    peta
    -0.50
    POSITIVE LOGITS
     sign
    1.85
     Sign
    1.80
    Sign
    1.68
    sign
    1.52
     SIGN
    1.49
    SIGN
    1.41
     signs
    1.38
     Signs
    1.34
     signo
    1.30
    Signs
    1.27
    Act Density 0.012%

    No Known Activations