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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	CG
    -0.07
    _tw
    -0.07
     sausage
    -0.07
    rone
    -0.07
    _CA
    -0.07
     Serve
    -0.06
     shaped
    -0.06
     र
    -0.06
    ंस
    -0.06
    '];
↵
↵
    -0.06
    POSITIVE LOGITS
    aphrag
    0.06
     dětí
    0.06
     прод
    0.06
    ubbles
    0.06
     تحت
    0.06
     signup
    0.06
    tes
    0.06
    oloj
    0.06
     distancia
    0.05
    .labels
    0.05
    Act Density 0.006%

    No Known Activations