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

    Neuronpedia

    INDEX
    Explanations

    set

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Algorithm
    -0.08
     kaž
    -0.08
    Obama
    -0.08
     beds
    -0.08
     Selena
    -0.08
    Officer
    -0.08
    emma
    -0.08
    gpu
    -0.08
    	ptr
    -0.08
    Gpu
    -0.07
    POSITIVE LOGITS
     tarjo
    0.07
    zer
    0.07
    -bas
    0.07
    tabs
    0.07
    za
    0.07
     негізгі
    0.07
     bref
    0.07
     құрыл
    0.07
     CH
    0.07
    zal
    0.07
    Act Density 0.000%

    No Known Activations