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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to emotional support and communication

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

    differentiate wrt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     &___
    -0.52
    arakhand
    -0.47
    windowFixed
    -0.43
    gridy
    -0.43
    IVEREF
    -0.41
    ]=>
    -0.40
    EDEFAULT
    -0.40
    StoryboardSegue
    -0.39
    GEBURTS
    -0.38
    szönöm
    -0.37
    POSITIVE LOGITS
    出版年
    0.65
     autorytatywna
    0.54
     springfox
    0.53
    Kaynakça
    0.51
     وتسجيلات
    0.50
    Referanser
    0.47
    MLLoader
    0.47
     noDo
    0.47
     transfieras
    0.45
    Partager
    0.45
    Act Density 0.001%

    No Known Activations