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

    Neuronpedia

    INDEX
    Explanations

    desired format or output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     necesidad
    0.49
     необходимости
    0.44
     attempting
    0.42
     deciding
    0.42
     choosing
    0.42
    akta
    0.41
     entscheiden
    0.41
     Interesse
    0.41
     wishing
    0.40
     Bedür
    0.40
    POSITIVE LOGITS
     outcome
    0.69
     behaviour
    0.60
     behavior
    0.59
     outcomes
    0.58
    outcome
    0.55
    behaviour
    0.49
     comportamiento
    0.49
    performance
    0.47
     comportement
    0.46
    Outcome
    0.46
    Act Density 0.018%

    No Known Activations