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
     municipal
    -0.06
    ;
    -0.06
     recycle
    -0.06
     ；
    -0.06
     Πλη
    -0.06
     Blanc
    -0.06
     frankly
    -0.06
     Carry
    -0.06
    steps
    -0.06
     SP
    -0.06
    POSITIVE LOGITS
     Image
    0.07
    φαρ
    0.07
     inherited
    0.06
    achines
    0.06
     aden
    0.06
    plx
    0.06
     gl
    0.06
     Voj
    0.06
    _peer
    0.06
    erdings
    0.06
    Act Density 0.000%

    No Known Activations