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
     Validators
    -0.07
    ucus
    -0.06
    samp
    -0.06
    اورزی
    -0.06
    _yaw
    -0.06
    abile
    -0.06
    	glm
    -0.06
    ipy
    -0.06
    _Construct
    -0.06
     QCOMPARE
    -0.06
    POSITIVE LOGITS
     обычно
    0.07
     Lind
    0.07
    阶段
    0.07
     Одна
    0.07
     combined
    0.07
     Combined
    0.06
    份
    0.06
     Equ
    0.06
    願い
    0.06
     Equation
    0.06
    Act Density 0.010%

    No Known Activations