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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    licenses
    -0.07
     Meat
    -0.07
    structors
    -0.06
    .Contains
    -0.06
     cls
    -0.06
    Teachers
    -0.06
     Astronomy
    -0.06
    phoneNumber
    -0.06
     जबक
    -0.06
    .context
    -0.06
    POSITIVE LOGITS
    	RTLU
    0.06
     الميلاد
    0.06
    -danger
    0.06
     sane
    0.06
     EM
    0.06
     legisl
    0.06
     GE
    0.06
     gid
    0.06
    Solar
    0.06
     nodo
    0.06
    Act Density 0.032%

    No Known Activations