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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fat
    -0.07
     смер
    -0.06
     bàn
    -0.06
    Officials
    -0.06
     como
    -0.06
    ilated
    -0.06
     guarded
    -0.06
     blij
    -0.06
    ृष
    -0.06
     Patio
    -0.06
    POSITIVE LOGITS
    ylül
    0.06
    <w
    0.06
    lining
    0.06
    .In
    0.06
    ับร
    0.06
    	pw
    0.06
     듣
    0.06
    객
    0.06
    inkel
    0.06
    jamin
    0.06
    Act Density 0.000%

    No Known Activations