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

    Neuronpedia

    INDEX
    Explanations

    documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disclosed
    -0.07
     seperti
    -0.06
     حد
    -0.06
    _completion
    -0.06
     quitting
    -0.06
     ctl
    -0.06
     ++)
    -0.06
     abandoning
    -0.06
    ˆ
    -0.06
     beyond
    -0.06
    POSITIVE LOGITS
    Basic
    0.07
    ablytyped
    0.07
     cane
    0.07
     oy
    0.07
    .vs
    0.07
    _eng
    0.07
    Hz
    0.06
     Basic
    0.06
    ilies
    0.06
     Costs
    0.06
    Act Density 0.009%

    No Known Activations