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

    Neuronpedia

    INDEX
    Explanations

    in the meantime

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вигляді
    0.88
     формы
    0.81
     postaci
    0.76
     formas
    0.74
     형태로
    0.73
     kwamba
    0.72
     Forms
    0.72
     виды
    0.71
     являются
    0.71
    +.
    0.71
    POSITIVE LOGITS
     case
    1.47
     caso
    1.18
     end
    1.14
     случае
    1.12
    case
    1.08
     meantime
    1.06
     geval
    1.05
    場合
    1.01
    Case
    1.00
     경우
    1.00
    Act Density 0.016%

    No Known Activations