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

    Neuronpedia

    INDEX
    Explanations

    Bacteria

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Erwer
    -0.08
     לב
    -0.08
     IAction
    -0.08
     Hiz
    -0.07
     іст
    -0.07
    _aw
    -0.07
    _GET
    -0.07
    _adv
    -0.07
     الآخر
    -0.07
     Levy
    -0.07
    POSITIVE LOGITS
     environments
    0.10
     ambientes
    0.10
     workplace
    0.08
    环境
    0.08
    вад
    0.08
     bathroom
    0.08
    /tmp
    0.08
     городской
    0.08
     sludge
    0.08
     वातावरण
    0.08
    Act Density 0.014%

    No Known Activations