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

    Neuronpedia

    INDEX
    Explanations

    non-commercial license

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     करोगे
    0.47
     형성
    0.47
    形成的
    0.44
    trades
    0.44
     formed
    0.43
     발생
    0.43
     uncond
    0.43
     displ
    0.43
    created
    0.42
    Occurrence
    0.42
    POSITIVE LOGITS
    ры
    0.50
     práctica
    0.49
    ándolo
    0.47
    ándola
    0.47
    ティング
    0.46
     sencillo
    0.46
     japonés
    0.46
     instituciones
    0.46
     música
    0.46
     широ
    0.45
    Act Density 0.001%

    No Known Activations