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

    Neuronpedia

    INDEX
    Explanations

    from you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    p
    0.57
    u
    0.52
    ser
    0.47
    self
    0.47
    et
    0.46
    ta
    0.46
     पैर
    0.46
    m
    0.45
    g
    0.45
    b
    0.45
    POSITIVE LOGITS
     balcon
    0.55
     кора
    0.55
     cubrir
    0.55
     relativamente
    0.54
     наличи
    0.53
     freer
    0.51
     آذ
    0.50
     relâche
    0.50
     undulating
    0.50
     dxc
    0.50
    Act Density 0.000%

    No Known Activations