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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating probability or certainty about outcomes

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

    you often want to use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.47
    aspetto
    -0.45
     namorados
    -0.44
    Portail
    -0.43
     luzes
    -0.43
    Дереккөздер
    -0.43
     your
    -0.42
     surla
    -0.41
    Cyfeiriadau
    -0.41
     everything
    -0.41
    POSITIVE LOGITS
    SequentialGroup
    0.42
     محفوظة
    0.40
     AssemblyCompany
    0.38
     jsPsych
    0.38
     gestorben
    0.37
     parati
    0.36
    @@@@@
    0.36
     Rote
    0.36
    resave
    0.35
    Mediabestanden
    0.35
    Act Density 0.102%

    No Known Activations