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

    Neuronpedia

    INDEX
    Explanations

    references to specific names and characters

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

    First names

    np_acts-logits-general · gemini-2.0-flash

    names in sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Darius
    -0.57
    Darren
    -0.54
     Darren
    -0.54
     Dutchman
    -0.53
     Wilfred
    -0.53
    Rodney
    -0.52
    ‍♂️
    -0.52
     Dwayne
    -0.52
     Eric
    -0.51
    carlos
    -0.51
    POSITIVE LOGITS
    <?
    0.52
     Ann
    0.49
     rostros
    0.48
    Rose
    0.46
    Ann
    0.45
    unzel
    0.43
    Grace
    0.43
     Rose
    0.43
     oídos
    0.43
     Grace
    0.42
    Act Density 0.763%

    No Known Activations