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

    Neuronpedia

    INDEX
    Explanations

    versus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     деревян
    -0.07
    ид
    -0.07
    -front
    -0.07
    .serv
    -0.06
     estudiantes
    -0.06
     бук
    -0.06
    zę
    -0.06
     gradu
    -0.06
     ال
    -0.06
    Pale
    -0.06
    POSITIVE LOGITS
     Mounted
    0.07
     IIC
    0.06
    _mount
    0.06
    =file
    0.06
     emptied
    0.06
     Near
    0.06
     widget
    0.06
     mural
    0.06
     nested
    0.06
     posicion
    0.06
    Act Density 0.014%

    No Known Activations