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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    μβρίου
    -0.07
     Mas
    -0.06
    _SUR
    -0.06
     enviar
    -0.06
     descri
    -0.06
    Ahead
    -0.06
     انج
    -0.06
    anyak
    -0.06
    Sanders
    -0.06
    —we
    -0.06
    POSITIVE LOGITS
     accessToken
    0.07
    生物
    0.06
    .skills
    0.06
     còn
    0.06
    験
    0.06
    효
    0.06
     ’
    0.06
     tecr
    0.06
    έρα
    0.06
    ่อ
    0.06
    Act Density 0.046%

    No Known Activations