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

    Neuronpedia

    INDEX
    Explanations

    -s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     confronting
    -0.07
    /(
    -0.07
     fourteen
    -0.07
    oralType
    -0.06
     인터
    -0.06
    hud
    -0.06
     ">
    -0.06
    unj
    -0.06
    .colorbar
    -0.06
    Scheduler
    -0.06
    POSITIVE LOGITS
     grapes
    0.08
    iking
    0.07
     temps
    0.06
    ामक
    0.06
    FFF
    0.06
    -S
    0.06
     знаход
    0.06
     shares
    0.06
     COL
    0.06
    σί
    0.06
    Act Density 0.002%

    No Known Activations