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

    Neuronpedia

    INDEX
    Explanations

    causal relationships or reasons behind actions

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

    explaining a reason

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initComponents
    -0.75
    NameInMap
    -0.69
     nakalista
    -0.66
     Verſ
    -0.66
    Geplaatst
    -0.65
     Taktlose
    -0.65
     queſta
    -0.65
     imagui
    -0.65
    <unused41>
    -0.65
    <unused68>
    -0.65
    POSITIVE LOGITS
     because
    0.52
     porque
    0.41
    是因為
    0.40
    because
    0.38
    是因为
    0.36
    เพราะ
    0.35
    łk
    0.34
     wanted
    0.33
    EC
    0.33
     and
    0.31
    Act Density 0.048%

    No Known Activations