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

    Neuronpedia

    INDEX
    Explanations

    references to community engagement and collaboration in problem-solving contexts

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

    new ways of thinking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initComponents
    -0.70
    principalColumn
    -0.69
    bewerken
    -0.61
     pinulongan
    -0.56
    enderror
    -0.54
    蚪
    -0.54
    actionMode
    -0.52
    aarrggbb
    -0.51
     faſt
    -0.51
     ſte
    -0.50
    POSITIVE LOGITS
     interesting
    0.38
     intéressant
    0.36
     leren
    0.36
     interessanti
    0.34
     saludable
    0.34
     interesante
    0.33
     interesantes
    0.33
     daardoor
    0.33
     Zeugen
    0.33
     Ursache
    0.33
    Act Density 0.107%

    No Known Activations