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

    Neuronpedia

    INDEX
    Explanations

    negative statements or expressions of discontent

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

    not want, fit, contained, trust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.54
    PerformLayout
    -0.53
    enderror
    -0.53
    EndInit
    -0.51
    BIÉN
    -0.48
    fjspx
    -0.47
    AndEndTag
    -0.46
    BeginInit
    -0.45
    invokeLater
    -0.45
    ंदीखरीदारी
    -0.44
    POSITIVE LOGITS
    removeAttribute
    0.47
    isNot
    0.43
    不
    0.42
     glace
    0.42
    removeAttr
    0.40
    人不
    0.40
     non
    0.39
    ilt
    0.39
     Non
    0.38
    assertFalse
    0.38
    Act Density 0.319%

    No Known Activations