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

    Neuronpedia

    INDEX
    Explanations

    B

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	K
    -0.06
    AMIL
    -0.06
    _KERNEL
    -0.06
    "People
    -0.06
     อ
    -0.06
    _ALPHA
    -0.06
     measured
    -0.06
     съ
    -0.06
    _STENCIL
    -0.06
     kommer
    -0.06
    POSITIVE LOGITS
    inct
    0.07
    .equ
    0.07
    ону
    0.07
    roperty
    0.06
     التن
    0.06
     Ab
    0.06
    As
    0.06
    جب
    0.06
     陈
    0.06
     subsection
    0.06
    Act Density 0.006%

    No Known Activations