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

    Neuronpedia

    INDEX
    Explanations

    separators followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ī
    0.70
    ))
    0.52
    É
    0.52
    za
    0.49
    Ĭ
    0.47
    INA
    0.46
    GI
    0.46
    Á
    0.46
    Б
    0.45
    Ä
    0.44
    POSITIVE LOGITS
    <unused664>
    0.67
    <unused595>
    0.61
    <unused1085>
    0.61
    <unused1020>
    0.60
    <unused626>
    0.60
    <unused147>
    0.59
    <unused387>
    0.59
    <unused616>
    0.59
    <unused757>
    0.58
    <unused1062>
    0.57
    Act Density 0.000%

    No Known Activations