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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing emotions, beauty, and moral judgment

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

    what a/an/how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.46
    :+:
    -0.44
     صوتيه
    -0.42
    celotti
    -0.42
     оригіналу
    -0.41
    IntoConstraints
    -0.41
    entista
    -0.40
    istocene
    -0.38
    MemoryWarning
    -0.37
    Mermaid
    -0.36
    POSITIVE LOGITS
    InputBorder
    0.56
    stateProvider
    0.52
    ftagPool
    0.45
    多么
    0.44
    indeed
    0.44
     jadx
    0.44
    FormTagHelper
    0.43
    네
    0.41
    0.40
    EndInit
    0.40
    Act Density 0.086%

    No Known Activations