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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    addElement
    -0.06
     '/',
    -0.06
    Robot
    -0.06
    <Model
    -0.06
    ятся
    -0.06
     Studi
    -0.06
     dealloc
    -0.06
    Χ
    -0.06
     height
    -0.06
     μου
    -0.06
    POSITIVE LOGITS
    -away
    0.07
    (MPI
    0.07
    acyj
    0.06
    織
    0.06
     Pam
    0.06
    ;br
    0.06
     squeezed
    0.06
     commissioners
    0.06
    Rol
    0.06
     parler
    0.06
    Act Density 0.008%

    No Known Activations