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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and exclamations in response to situations

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

    exclamations and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.61
    хьтан
    -0.53
     ruinas
    -0.50
     quieras
    -0.46
     snippetHide
    -0.45
     felicitación
    -0.45
     curiosidad
    -0.45
     cremallera
    -0.45
     campamento
    -0.44
     debilidad
    -0.44
    POSITIVE LOGITS
    MessageTagHelper
    0.42
    xtext
    0.40
    iotensin
    0.40
    jsonwebtoken
    0.39
    !!!
    0.39
    SourceChecksum
    0.38
     propOrder
    0.36
    лич
    0.36
    änner
    0.36
    ble
    0.36
    Act Density 0.048%

    No Known Activations