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

    Neuronpedia

    INDEX
    Explanations

    academic publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     professions
    -0.07
    _ts
    -0.07
    Hugh
    -0.06
     NI
    -0.06
     ni
    -0.06
    Bold
    -0.06
     gle
    -0.06
    'av
    -0.06
     taller
    -0.06
    Sales
    -0.06
    POSITIVE LOGITS
    فة
    0.07
    uelve
    0.07
     appoint
    0.06
     pomáh
    0.06
    	RTDBG
    0.06
     SMB
    0.06
     vyu
    0.06
    енты
    0.06
     слов
    0.06
    	final
    0.06
    Act Density 0.016%

    No Known Activations