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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating mathematical or theoretical concepts and relationships

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

    concepts like ideology, representation, or secrets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fjspx
    -0.55
     kasarigan
    -0.54
    Personensuche
    -0.53
    Hentet
    -0.51
    verwijspagina
    -0.50
     autorytatywna
    -0.47
    VolleyError
    -0.46
    Източници
    -0.46
    يكب
    -0.46
    SBATCH
    -0.45
    POSITIVE LOGITS
     culturelles
    0.40
     instituciones
    0.38
    ättä
    0.37
    üyor
    0.37
    AutoScaleMode
    0.36
     totiž
    0.36
    wość
    0.35
     actuaciones
    0.34
     instituições
    0.34
    quedo
    0.34
    Act Density 0.354%

    No Known Activations