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

    Neuronpedia

    INDEX
    Explanations

    positive assessments or evaluations

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

    good qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dabei
    -0.45
    Portály
    -0.40
     INFL
    -0.38
     INNOV
    -0.37
    طراحی
    -0.36
    たった
    -0.36
    Membrane
    -0.36
     actions
    -0.36
    memoized
    -0.35
    rungsseite
    -0.35
    POSITIVE LOGITS
     good
    1.23
    Good
    1.10
    good
    1.09
     Good
    1.06
     GOOD
    0.95
     buen
    0.93
    GOOD
    0.92
     buone
    0.92
     buoni
    0.89
     decent
    0.88
    Act Density 0.023%

    No Known Activations