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

    Neuronpedia

    INDEX
    Explanations

    into phrases or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Schools
    0.47
     terreno
    0.45
    Newman
    0.45
    anzas
    0.44
    Cas
    0.44
     estructuras
    0.42
    D
    0.42
     ess
    0.40
     ar
    0.40
     escolas
    0.40
    POSITIVE LOGITS
     απο
    0.52
    ي
    0.52
    ící
    0.50
    ஔ
    0.48
     новую
    0.47
     сту
    0.46
    さて
    0.46
    separated
    0.46
    ﺔ
    0.46
    фро
    0.45
    Act Density 0.000%

    No Known Activations