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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compulsory
    -0.07
    Frameworks
    -0.07
     enviado
    -0.07
    ौकर
    -0.07
     punishing
    -0.06
     parks
    -0.06
     sanct
    -0.06
    -function
    -0.06
    ザイン
    -0.06
     )↵↵↵↵↵↵↵↵
    -0.06
    POSITIVE LOGITS
    {:
    0.07
     SS
    0.06
     some
    0.06
    (Value
    0.06
    -after
    0.06
    >true
    0.06
    (orig
    0.06
     strengthens
    0.06
    fortunately
    0.06
     Size
    0.06
    Act Density 0.004%

    No Known Activations