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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions, exceptions, or elaborations related to a subject

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

    phrases introduced by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     corre
    -0.38
    RepeatedField
    -0.33
     Oester
    -0.33
     corr
    -0.32
     legislat
    -0.31
     gh
    -0.31
     membranes
    -0.30
     catal
    -0.30
     facilit
    -0.30
     conne
    -0.30
    POSITIVE LOGITS
     nahilalakip
    0.89
     autorytatywna
    0.68
    AutoScaleMode
    0.63
    CreateModel
    0.61
     ujednoznacz
    0.60
     ब्रेकडाउन
    0.59
     propOrder
    0.58
    ፩
    0.58
    Personendaten
    0.58
    Diweddarwch
    0.58
    Act Density 0.187%

    No Known Activations