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

    Neuronpedia

    INDEX
    Explanations

    negations and inconsistently formatted statements

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

    true or false evaluations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.53
     Мексичка
    -0.47
    posedge
    -0.44
    MethodManager
    -0.39
    ไง
    -0.39
    よかった
    -0.39
    VELAND
    -0.39
     الحره
    -0.38
    zeba
    -0.38
    變得
    -0.37
    POSITIVE LOGITS
    Errorf
    0.56
    ❌
    0.41
    ixote
    0.41
    ilarang
    0.41
    holz
    0.40
    toBeTruthy
    0.40
    ziasztok
    0.39
     because
    0.39
    httphttps
    0.39
     çünkü
    0.38
    Act Density 0.189%

    No Known Activations