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

    Neuronpedia

    INDEX
    Explanations

    Vladimir

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    仔
    -0.07
    OU
    -0.07
     descendant
    -0.06
    bij
    -0.06
     cach
    -0.06
     sist
    -0.06
     becer
    -0.06
     memo
    -0.06
     раб
    -0.06
     airy
    -0.06
    POSITIVE LOGITS
     Vladimir
    0.13
     Vlad
    0.08
    getDoctrine
    0.07
    _TRACE
    0.07
     Muhammad
    0.07
     Multimedia
    0.07
    sında
    0.07
     disagreement
    0.07
    LANGADM
    0.06
    Dur
    0.06
    Act Density 0.003%

    No Known Activations