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

    Neuronpedia

    INDEX
    Explanations

    team

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ಕ್ರಮ
    -0.09
     comod
    -0.08
     ബാധ
    -0.08
    _layer
    -0.08
     വിവ
    -0.07
     മാറ
    -0.07
     Halb
    -0.07
     Layer
    -0.07
    ะ
    -0.07
     ವಿವ
    -0.07
    POSITIVE LOGITS
     కలిసి
    0.10
    ினர்
    0.09
     responsible
    0.09
     behind
    0.09
    leden
    0.09
    🏼
    0.09
     tomonidan
    0.09
     دار
    0.09
     birlikte
    0.09
     جمع
    0.09
    Act Density 0.062%

    No Known Activations