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

    Neuronpedia

    INDEX
    Explanations

    asterisk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Me
    -0.08
    emouth
    -0.08
    กาย
    -0.07
     Ampl
    -0.07
     Ink
    -0.07
     exhaustion
    -0.07
    生产能力
    -0.07
     MOTOR
    -0.07
    ające
    -0.07
    “Our
    -0.07
    POSITIVE LOGITS
    小說
    0.08
    折
    0.07
     troubling
    0.07
     birçok
    0.07
    веч
    0.07
     user
    0.07
    ules
    0.07
     depois
    0.07
     sometimes
    0.06
    公众号
    0.06
    Act Density 0.009%

    No Known Activations