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
    δες
    -0.06
     chairs
    -0.06
    iking
    -0.06
    	q
    -0.06
     Foster
    -0.06
     Identified
    -0.06
     Coff
    -0.06
     karş
    -0.06
     Rectangle
    -0.06
     Overse
    -0.06
    POSITIVE LOGITS
    /left
    0.07
     педагог
    0.06
     eros
    0.06
     Intercept
    0.06
    ishlist
    0.06
    των
    0.06
     сог
    0.06
    ану
    0.06
    ियर
    0.06
    TON
    0.06
    Act Density 0.000%

    No Known Activations