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

    Neuronpedia

    INDEX
    Explanations

    behavior and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ал
    0.52
    ЛИ
    0.52
    יל
    0.52
    Ы
    0.51
    kében
    0.49
    ｉ
    0.49
    ба
    0.49
    фи
    0.48
    фа
    0.48
    че
    0.48
    POSITIVE LOGITS
     don
    0.46
     stratég
    0.45
     avec
    0.44
     kombin
    0.44
     uso
    0.44
     algorit
    0.44
     de
    0.43
     poder
    0.43
     accessories
    0.43
     using
    0.42
    Act Density 0.326%

    No Known Activations