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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Daly
    -0.06
     Corps
    -0.06
     toolbox
    -0.06
    exercise
    -0.06
    Harness
    -0.06
     заліз
    -0.06
    bara
    -0.06
    218
    -0.06
     negro
    -0.06
    cer
    -0.06
    POSITIVE LOGITS
    么
    0.07
    ْع
    0.06
     cha
    0.06
    draw
    0.06
     デ
    0.06
    。また
    0.06
     begr
    0.06
    ジア
    0.06
    論
    0.06
     )}↵
    0.06
    Act Density 0.172%

    No Known Activations