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

    Neuronpedia

    INDEX
    Explanations

    stress and forces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Traits
    0.44
     sticky
    0.43
    sticky
    0.41
     Sticky
    0.40
    textured
    0.40
     Brun
    0.40
    Properties
    0.39
    preprocessing
    0.39
    testing
    0.39
     experimenting
    0.39
    POSITIVE LOGITS
     stresses
    1.14
     stress
    0.93
     stres
    0.82
    ストレス
    0.81
    stress
    0.77
     voltages
    0.76
     Stress
    0.75
     forces
    0.73
    Stress
    0.73
     estrés
    0.68
    Act Density 0.018%

    No Known Activations