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

    Neuronpedia

    INDEX
    Explanations

    structural components of code, particularly conditional statements and control flow elements

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

    user method labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    发表于
    -0.40
    境
    -0.33
    리고
    -0.31
    ⓧ
    -0.31
    继续
    -0.30
     merec
    -0.29
     gidi
    -0.29
    hely
    -0.29
     کف
    -0.29
     отличи
    -0.28
    POSITIVE LOGITS
    ReusableCell
    0.66
     AssemblyCompany
    0.66
     myſelf
    0.65
    ContentAlignment
    0.63
     pleaſure
    0.63
     defaultstate
    0.61
     raiſ
    0.60
    +#+#
    0.60
     fhort
    0.59
     kasarigan
    0.59
    Act Density 0.003%

    No Known Activations