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

    Neuronpedia

    INDEX
    Explanations

    must

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     must
    -2.36
    must
    -2.31
    Must
    -2.14
     Must
    -2.05
    MUST
    -1.62
     MUST
    -1.43
     måste
    -1.42
     doivent
    -1.37
     muft
    -1.27
    必须
    -1.26
    POSITIVE LOGITS
    ers
    0.66
     express
    0.65
     be
    0.65
     stay
    0.62
     give
    0.61
     understand
    0.61
     engage
    0.60
     organise
    0.60
     take
    0.60
     meet
    0.59
    Act Density 0.068%

    No Known Activations