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

    Neuronpedia

    INDEX
    Explanations

    terms related to inverters and inversions in technical contexts

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

    inverter, inversion, inverted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.62
     noDo
    -0.56
    dawg
    -0.55
    hability
    -0.50
    Encourage
    -0.50
    fjspx
    -0.47
    enterOuterAlt
    -0.47
    Ability
    -0.46
     estre
    -0.46
    Butch
    -0.46
    POSITIVE LOGITS
     Inver
    0.71
    Inver
    0.65
     inver
    0.64
     invert
    0.63
     inverter
    0.63
    Invert
    0.57
     inversion
    0.56
     Inverter
    0.54
    invert
    0.49
    inver
    0.48
    Act Density 0.031%

    No Known Activations