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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating totality or an emphasis on all-encompassing terms

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

    for all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -0.45
     pleaſure
    -0.38
    MemoryWarning
    -0.35
     itſelf
    -0.35
     ſta
    -0.34
    ſelves
    -0.34
     houſe
    -0.33
     Résultat
    -0.33
    Ic
    -0.32
    ModelAdmin
    -0.32
    POSITIVE LOGITS
    tawesome
    0.65
     Infórmanos
    0.58
     autorytatywna
    0.57
    WebElementEntity
    0.55
     >=",
    0.54
    fjspx
    0.52
     kasarigan
    0.52
     otomatig
    0.52
    Портали
    0.50
    Guinea
    0.50
    Act Density 0.015%

    No Known Activations