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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝖋
    -0.07
    통
    -0.07
    營
    -0.07
     seiner
    -0.07
     /[
    -0.07
    מפקד
    -0.07
     balance
    -0.06
    逻
    -0.06
     %[
    -0.06
     rá
    -0.06
    POSITIVE LOGITS
    🌶
    0.08
     plethora
    0.08
    حتياج
    0.08
    Finished
    0.07
    adopt
    0.07
    GEST
    0.07
    ớ
    0.07
    ]initWith
    0.07
     potrze
    0.07
     opposed
    0.07
    Act Density 0.001%

    No Known Activations