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

    Neuronpedia

    INDEX
    Explanations

    risk assessment, tolerance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bic
    0.96
    corder
    0.82
    ца
    0.80
    rences
    0.80
    жную
    0.79
    debugging
    0.77
    cí
    0.77
    sion
    0.77
    örungen
    0.77
    拯救
    0.77
    POSITIVE LOGITS
     assessment
    1.36
     appetite
    1.33
     averse
    1.27
     Assessment
    1.26
    ier
    1.26
     assessments
    1.22
    Assessment
    1.21
     posed
    1.19
     profile
    1.15
    assessment
    1.14
    Act Density 0.086%

    No Known Activations