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

    Neuronpedia

    INDEX
    Explanations

    credibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Plasma
    -0.07
    _SORT
    -0.06
    amak
    -0.06
    produto
    -0.06
     resulting
    -0.06
    쿠
    -0.06
     Deutschland
    -0.06
    _primitive
    -0.06
    _round
    -0.06
     QUEST
    -0.06
    POSITIVE LOGITS
     credibility
    0.14
     credible
    0.12
    credible
    0.07
     discredit
    0.07
     капіт
    0.07
     incred
    0.07
     들
    0.06
    ris
    0.06
     Crow
    0.06
     Rory
    0.06
    Act Density 0.005%

    No Known Activations