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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Probability
    -0.07
     friendship
    -0.07
     Celtic
    -0.06
    Pi
    -0.06
    Doctors
    -0.06
    Bars
    -0.06
    Putting
    -0.06
     Rape
    -0.06
    Financial
    -0.06
     після
    -0.06
    POSITIVE LOGITS
     Terminator
    0.07
     filename
    0.06
    (kernel
    0.06
    _MESH
    0.06
    ie
    0.06
    adays
    0.06
    izzly
    0.06
    _Delete
    0.06
    Bundle
    0.06
    yna
    0.06
    Act Density 0.011%

    No Known Activations