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

    Neuronpedia

    INDEX
    Explanations

    parenthetical references, particularly those related to names or titles

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

    names before marriage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.67
     invokingState
    -0.63
    setVerticalGroup
    -0.60
    Autoritní
    -0.59
    GEBURTSDATUM
    -0.57
    EndInit
    -0.56
    #+#
    -0.56
    SequentialGroup
    -0.56
     صوتيه
    -0.54
    évaluateur
    -0.53
    POSITIVE LOGITS
     dezelve
    0.54
    ьаж
    0.49
     married
    0.38
    former
    0.37
    Lastname
    0.37
    Apellido
    0.36
     verheir
    0.36
     former
    0.35
    textfield
    0.35
    lastname
    0.35
    Act Density 0.003%

    No Known Activations