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

    Neuronpedia

    INDEX
    Explanations

    words associated with vulnerability or susceptibility to negative health conditions

    oai_token-act-pair · gemini-2.0-flash

    vulnerability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     n
    -0.48
    GEBURTSDATUM
    -0.47
    dres
    -0.46
    heu
    -0.45
     met
    -0.43
    ukup
    -0.43
     som
    -0.41
     dar
    -0.41
    circ
    -0.41
     mit
    -0.41
    POSITIVE LOGITS
     poffible
    0.79
    出版年
    0.79
     susceptibility
    0.74
     itſelf
    0.72
     fubject
    0.69
    ſelves
    0.69
    сылкі
    0.68
     myſelf
    0.67
     متعلقه
    0.67
     ddelweddau
    0.66
    Act Density 2.163%

    No Known Activations