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

    Neuronpedia

    INDEX
    Explanations

    directly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     especializado
    0.47
     spezielle
    0.46
     spezial
    0.45
     ఒకటి
    0.45
     tätig
    0.45
     spezi
    0.44
     interventions
    0.44
     €,
    0.44
     specialization
    0.43
     ulei
    0.41
    POSITIVE LOGITS
    osamente
    0.42
    ма
    0.42
    ю
    0.42
     이름을
    0.41
    т
    0.41
    alignment
    0.40
    दास
    0.40
     matching
    0.40
    matching
    0.40
    sides
    0.40
    Act Density 0.001%

    No Known Activations