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

    Neuronpedia

    INDEX
    Explanations

    difficulty across languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Launch
    0.38
    Modified
    0.38
    Pause
    0.37
    OnInit
    0.36
    (+)
    0.35
     Launch
    0.35
     сразу
    0.35
    Telemetry
    0.35
     personalization
    0.35
    MGMT
    0.34
    POSITIVE LOGITS
     Rebecca
    0.47
     dificultades
    0.47
     kesulitan
    0.45
     difficultés
    0.45
    uan
    0.44
     dificult
    0.43
     dificuldades
    0.43
     difficoltà
    0.42
     dific
    0.42
     meningkat
    0.41
    Act Density 0.000%

    No Known Activations