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
    Vars
    -0.07
     も
    -0.06
     hemen
    -0.06
     IllegalAccessException
    -0.06
     PLA
    -0.06
     defe
    -0.06
    ウィ
    -0.06
     projectiles
    -0.06
     Parks
    -0.06
    زان
    -0.06
    POSITIVE LOGITS
     pneumonia
    0.07
     Wong
    0.06
    Consider
    0.06
    .setAdapter
    0.06
     lied
    0.06
     sealed
    0.06
     evidence
    0.06
    Ultra
    0.06
     ElementRef
    0.06
     shuttle
    0.06
    Act Density 0.000%

    No Known Activations