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

    Neuronpedia

    INDEX
    Explanations

    forms and types of various concepts or classifications

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

    forms of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.40
     dAtA
    -0.39
    ration
    -0.38
     sweet
    -0.38
     corne
    -0.37
     pull
    -0.37
     seeds
    -0.36
     gord
    -0.36
    Vitals
    -0.35
    OrNil
    -0.34
    POSITIVE LOGITS
     Formen
    1.06
     forms
    1.02
     formas
    1.00
     form
    0.97
     formes
    0.94
     FORMS
    0.93
     bentuk
    0.93
     Bentuk
    0.91
     формы
    0.90
    形式
    0.87
    Act Density 0.076%

    No Known Activations