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

    Neuronpedia

    INDEX
    Explanations

    terms related to durability and strength

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

    toughness, resilience, hardness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.68
    enumii
    -0.50
    LLocation
    -0.48
    ConstraintMaker
    -0.47
    ніципалі
    -0.47
    MLLoader
    -0.46
     Lettres
    -0.46
    WriteBarrier
    -0.45
    참고
    -0.44
    thâu
    -0.43
    POSITIVE LOGITS
    Tough
    0.90
     hardened
    0.89
     toughness
    0.88
    tough
    0.86
     Tough
    0.86
     harden
    0.81
     resilient
    0.77
     hardening
    0.74
     resilience
    0.71
    Resili
    0.70
    Act Density 0.029%

    No Known Activations