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
     onFailure
    -0.07
     Ald
    -0.07
    านคร
    -0.07
    _IMM
    -0.07
    )localObject
    -0.07
     підприємства
    -0.07
    ини
    -0.06
    _REFERER
    -0.06
     मण
    -0.06
    ิ่
    -0.06
    POSITIVE LOGITS
    част
    0.07
     ни
    0.07
    ASA
    0.06
    	then
    0.06
    RO
    0.06
     RPC
    0.06
     ditch
    0.06
     precisely
    0.05
     Couldn
    0.05
     coach
    0.05
    Act Density 0.002%

    No Known Activations