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

    Neuronpedia

    INDEX
    Explanations

    current states and recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uk
    0.52
    ungan
    0.49
    gut
    0.46
    gence
    0.45
     ውስ
    0.45
     невероят
    0.44
     ንጥረ
    0.44
    tu
    0.42
    umbling
    0.42
    smtb
    0.42
    POSITIVE LOGITS
     soluções
    0.58
     sesiones
    0.55
     aceste
    0.54
     experiencias
    0.54
     dares
    0.53
     durumda
    0.53
     insists
    0.52
     usuarios
    0.51
     presentes
    0.51
     salud
    0.50
    Act Density 0.002%

    No Known Activations