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

    Neuronpedia

    INDEX
    Explanations

    various expressions related to values and beliefs

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

    values and beliefs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.67
     miraculous
    -0.53
    ョ
    -0.50
    lotte
    -0.49
     يتيمه
    -0.47
    awaiter
    -0.46
     unpredictable
    -0.44
    addPreferredGap
    -0.44
     avoidable
    -0.43
    طبي
    -0.42
    POSITIVE LOGITS
     principles
    0.92
    principles
    0.87
     ideals
    0.85
     tenets
    0.82
     beliefs
    0.80
     Ideology
    0.79
     Principles
    0.78
     &___
    0.77
     Beliefs
    0.77
     philosophies
    0.75
    Act Density 0.083%

    No Known Activations