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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and type-checking operations

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

    instanceof checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.81
    niſſe
    -0.79
     ſind
    -0.78
    ロウィン
    -0.78
     Wiktionnaire
    -0.77
    <unused79>
    -0.77
    <unused14>
    -0.76
    <unused16>
    -0.76
    <unused8>
    -0.76
    [@BOS@]
    -0.76
    POSITIVE LOGITS
    .(*
    0.87
     instanceof
    0.63
    asInstanceOf
    0.55
    InstanceOf
    0.45
     any
    0.37
    ,
    0.36
    .(
    0.36
    closest
    0.36
    class
    0.36
    ly
    0.35
    Act Density 0.008%

    No Known Activations