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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical Text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kháu
    -0.52
    ncy
    -0.47
    nodoc
    -0.47
    letics
    -0.46
     par
    -0.45
     iprot
    -0.44
     Canon
    -0.44
    abetes
    -0.43
    ispiel
    -0.43
    Captcha
    -0.43
    POSITIVE LOGITS
    toyage
    0.60
     légiti
    0.58
     незавершена
    0.54
     roulant
    0.51
    mereka
    0.51
    lihatan
    0.51
     Thad
    0.50
    Tore
    0.50
     Tore
    0.50
     pacchetto
    0.49
    Act Density 0.003%

    No Known Activations