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

    Neuronpedia

    INDEX
    Explanations

    single

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -export
    -0.07
     takeover
    -0.07
     agriculture
    -0.07
     Mort
    -0.06
     grass
    -0.06
     near
    -0.06
     μο
    -0.06
    (md
    -0.06
    periences
    -0.06
    mayı
    -0.06
    POSITIVE LOGITS
    :$
    0.07
     пох
    0.07
    інь
    0.07
     dispens
    0.07
     bach
    0.06
     مستق
    0.06
    рач
    0.06
    templ
    0.06
    âl
    0.06
     XmlNode
    0.06
    Act Density 0.008%

    No Known Activations