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

    Neuronpedia

    INDEX
    Explanations

    code snippets and programming syntax within documentation

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

    Mathematical/code text followed by "which"

    np_acts-logits-general · gemini-2.0-flash

    $$

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zwiſchen
    -0.98
    <unused41>
    -0.96
    [@BOS@]
    -0.95
    <pad>
    -0.95
    <unused43>
    -0.95
    <unused14>
    -0.95
    <unused42>
    -0.95
    <unused28>
    -0.95
    <unused3>
    -0.95
    <unused8>
    -0.95
    POSITIVE LOGITS
    This
    0.40
    The
    0.36
    These
    0.35
    where
    0.35
    With
    0.34
    .
    0.32
    A
    0.31
    3
    0.31
    which
    0.31
     This
    0.31
    Act Density 0.560%

    No Known Activations