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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PATCH
    -0.07
    }:{
    -0.07
     RouteServiceProvider
    -0.06
    routeParams
    -0.06
     intimate
    -0.06
    _ATTACH
    -0.06
     Confeder
    -0.06
     onResponse
    -0.06
    	Register
    -0.06
    _buffers
    -0.06
    POSITIVE LOGITS
     anthem
    0.07
    ‌تواند
    0.06
     fines
    0.06
    hrs
    0.06
     dro
    0.06
    _tip
    0.06
     Ber
    0.06
    dia
    0.06
     エ
    0.06
    REW
    0.06
    Act Density 0.000%

    No Known Activations