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

    Neuronpedia

    INDEX
    Explanations

    the presence of verbs and indications of actions performed

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

    multilingual word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    -0.29
     
    -0.27
    、
    -0.24
    y
    -0.23
     Sternen
    -0.23
     or
    -0.23
     no
    -0.23
    c
    -0.22
     and
    -0.22
    h
    -0.21
    POSITIVE LOGITS
     zwiſchen
    1.28
    iſchen
    1.28
    [@BOS@]
    1.27
    <unused14>
    1.27
    <unused79>
    1.27
    niſſe
    1.27
    <unused74>
    1.27
    <unused43>
    1.27
    <unused28>
    1.27
    <unused41>
    1.27
    Act Density 0.014%

    No Known Activations