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

    Neuronpedia

    INDEX
    Explanations

    create configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     locomotor
    0.41
    ഗു
    0.40
     envoyé
    0.39
    output
    0.39
    llbracket
    0.39
     सोनू
    0.38
    ጠቃ
    0.38
     охра
    0.37
    ServletException
    0.36
     പര
    0.36
    POSITIVE LOGITS
     embedding
    0.39
    template
    0.37
     create
    0.36
     K
    0.35
     Creates
    0.35
     creando
    0.34
     Shader
    0.34
    raw
    0.34
     template
    0.34
     Create
    0.33
    Act Density 0.009%

    No Known Activations