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

    Neuronpedia

    INDEX
    Explanations

    code packages and versions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Risk
    -0.07
    \Backend
    -0.07
     شد
    -0.07
     gast
    -0.07
     couleur
    -0.07
     callee
    -0.07
    _sex
    -0.07
    گرد
    -0.07
     چرخ
    -0.06
    organizations
    -0.06
    POSITIVE LOGITS
    llib
    0.06
     황
    0.06
    YLON
    0.06
    aoke
    0.06
    igroup
    0.06
    inium
    0.06
    场
    0.05
     Australians
    0.05
    omit
    0.05
    ấ
    0.05
    Act Density 0.007%

    No Known Activations