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

    Neuronpedia

    INDEX
    Explanations

    freezing and frozen states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bakers
    -0.81
    ваги
    -0.73
     CLP
    -0.73
     cremation
    -0.72
     golfers
    -0.71
     germinate
    -0.71
     durchführen
    -0.71
     Megal
    -0.70
     Crucible
    -0.69
    heiz
    -0.69
    POSITIVE LOGITS
     freezing
    2.09
     frozen
    1.97
     freeze
    1.84
     Frozen
    1.81
    frozen
    1.76
    freeze
    1.75
     freezes
    1.73
    Freezing
    1.72
     Freeze
    1.70
     Freezing
    1.69
    Act Density 0.013%

    No Known Activations