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
     roadside
    -0.07
     uzak
    -0.06
     Concord
    -0.06
    TexParameteri
    -0.06
    709
    -0.06
    ुजर
    -0.06
    sylvania
    -0.06
    -Regular
    -0.06
     punishable
    -0.06
     hız
    -0.06
    POSITIVE LOGITS
     such
    0.07
     Populate
    0.07
     Self
    0.07
     TO
    0.07
     Ill
    0.07
     militants
    0.06
     appointments
    0.06
     причина
    0.06
    .archive
    0.06
     encouraging
    0.06
    Act Density 0.009%

    No Known Activations