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

    Neuronpedia

    INDEX
    Explanations

    XML files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }>
    -0.08
    _selected
    -0.07
     різні
    -0.06
    isans
    -0.06
    .WindowManager
    -0.06
    �
    -0.06
     wavelengths
    -0.06
     imposes
    -0.06
     постеп
    -0.06
    пат
    -0.06
    POSITIVE LOGITS
     神
    0.07
     '"+
    0.06
     occasionally
    0.06
     violates
    0.06
     violating
    0.06
    &w
    0.06
     hx
    0.06
     YELLOW
    0.06
     dáv
    0.06
     determ
    0.06
    Act Density 0.001%

    No Known Activations