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

    Neuronpedia

    INDEX
    Explanations

    terms related to destruction and elimination

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

    annihilation or elimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Audiodateien
    -0.44
     ostavi
    -0.42
     ivelany
    -0.40
     AssemblyVersion
    -0.38
     dė
    -0.37
    öffentlichen
    -0.37
    intahan
    -0.37
     izvē
    -0.37
     démocr
    -0.35
    GrantedAuthority
    -0.35
    POSITIVE LOGITS
     extermination
    0.99
     annihilation
    0.95
     annihil
    0.90
     elimination
    0.80
     wiped
    0.77
     annihilated
    0.76
    消灭
    0.74
     уничто
    0.74
    hilation
    0.74
     eliminate
    0.73
    Act Density 0.044%

    No Known Activations