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

    Neuronpedia

    INDEX
    Explanations

    blocks of text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     k
    -0.07
    来了
    -0.07
    perf
    -0.06
     Helmet
    -0.06
     Sov
    -0.06
     refinery
    -0.06
     save
    -0.06
     merge
    -0.06
     maxlen
    -0.06
     dolls
    -0.06
    POSITIVE LOGITS
     multimedia
    0.06
    اهای
    0.06
    uba
    0.06
    言わ
    0.06
    LoadIdentity
    0.06
    :mysql
    0.06
    íc
    0.06
    htt
    0.06
    .InvariantCulture
    0.05
    обще
    0.05
    Act Density 0.098%

    No Known Activations