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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Microsystems
    -0.06
    沒
    -0.06
     Pump
    -0.06
    amak
    -0.06
    Coding
    -0.06
     Maths
    -0.06
     bundan
    -0.06
     employs
    -0.06
    르
    -0.06
     Cyrus
    -0.06
    POSITIVE LOGITS
    184
    0.07
     nostalgic
    0.07
     clans
    0.06
     irq
    0.06
    Controllers
    0.06
    operative
    0.06
     haystack
    0.06
     üz
    0.06
    requency
    0.06
    (ALOAD
    0.06
    Act Density 0.022%

    No Known Activations