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

    Neuronpedia

    INDEX
    Explanations

    Advice/blog snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     milk
    -0.07
     Özel
    -0.06
     rod
    -0.06
    リス
    -0.06
     Milk
    -0.06
     наличии
    -0.06
    .Orders
    -0.06
     bacter
    -0.06
     Lah
    -0.06
     Fukushima
    -0.06
    POSITIVE LOGITS
    :**
    0.07
    Messaging
    0.07
     قال
    0.07
    věř
    0.06
    >w
    0.06
    _enc
    0.06
    Hang
    0.06
    eping
    0.06
    клад
    0.06
     complains
    0.06
    Act Density 0.345%

    No Known Activations